Computer Engineering Commons^™

Automated Brain Tumor Classifier With Deep Learning, Venkata Sai Krishna Chaitanya Kandula

Electronic Theses, Projects, and Dissertations

Brain Tumors are abnormal growth of cells within the brain that can be categorized as benign (non-cancerous) or malignant (cancerous). Accurate and timely classification of brain tumors is crucial for effective treatment planning and patient care. Medical imaging techniques like Magnetic Resonance Imaging (MRI) provide detailed visualizations of brain structures, aiding in diagnosis and tumor classification^[8].

In this project, we propose a brain tumor classifier applying deep learning methodologies to automatically classify brain tumor images without any manual intervention. The classifier uses deep learning architectures to extract and classify brain MRI images. Specifically, a Convolutional Neural Network (CNN) …

Enhancing Mobile App User Experience: A Deep Learning Approach For System Design And Optimization, Deepesh Haryani

Harrisburg University Dissertations and Theses

This paper presents a comprehensive framework for enhancing user experience in mobile applications through the integration of deep learning systems. The proposed system design encompasses various components, including data collection and preprocessing, model development and training, integration with mobile applications, dataset management service, model training service, model serving, hyperparameter optimization, metadata and artifact store, and workflow orchestration. Each component is meticulously designed with a focus on scalability, efficiency, isolation, and critical analysis. Innovative design principles are employed to ensure seamless integration, usability, and automation. Additionally, the paper discusses distributed training service design, advanced optimization techniques, and decision criteria for hyperparameter …

Extracting Dnn Architectures Via Runtime Profiling On Mobile Gpus, Dong Hyub Kim

Masters Theses

Due to significant investment, research, and development efforts over the past decade, deep neural networks (DNNs) have achieved notable advancements in classification and regression domains. As a result, DNNs are considered valuable intellectual property for artificial intelligence providers. Prior work has demonstrated highly effective model extraction attacks which steal a DNN, dismantling the provider’s business model and paving the way for unethical or malicious activities, such as misuse of personal data, safety risks in critical systems, or spreading misinformation. This thesis explores the feasibility of model extraction attacks on mobile devices using aggregated runtime profiles as a side-channel to leak …

Insights Into Cellular Evolution: Temporal Deep Learning Models And Analysis For Cell Image Classification, Xinran Zhao

Master's Theses

Understanding the temporal evolution of cells poses a significant challenge in developmental biology. This study embarks on a comparative analysis of various machine-learning techniques to classify cell colony images across different timestamps, thereby aiming to capture dynamic transitions of cellular states. By performing Transfer Learning with state-of-the-art classification networks, we achieve high accuracy in categorizing single-timestamp images. Furthermore, this research introduces the integration of temporal models, notably LSTM (Long Short Term Memory Network), R-Transformer (Recurrent Neural Network enhanced Transformer) and ViViT (Video Vision Transformer), to undertake this classification task to verify the effectiveness of incorporating temporal features into the classification …

Applications Of Predictive And Generative Ai Algorithms: Regression Modeling, Customized Large Language Models, And Text-To-Image Generative Diffusion Models, Suhaima Jamal

Electronic Theses and Dissertations

The integration of Machine Learning (ML) and Artificial Intelligence (AI) algorithms has radically changed predictive modeling and classification tasks, enhancing a multitude of domains with unprecedented analytical capabilities. Predictive modeling leverages ML and AI to forecast future trends or behaviors based on historical data, while classification tasks categorize data into distinct classes, from email filtering to medical diagnosis. Concurrently, text-to-image generation has emerged as a transformative potential, allowing visual content creation directly from textual descriptions. These advancements are pivotal in design, art, entertainment, and visual communication, as well as enhancing creativity and productivity. This work explores three significant studies in …

Deep Learning Frameworks For Accelerated Magnetic Resonance Image Reconstruction Without Ground Truths, Ibsa Kumara Jalata

Graduate Theses and Dissertations

Magnetic Resonance Imaging (MRI) is typically a slow process because of its sequential data acquisition. To speed up this process, MR acquisition is often accelerated by undersampling k-space signals and solving an ill-posed problem through a constrained optimization process. Image reconstruction from under-sampled data is posed as an inverse problem in traditional model-based learning paradigms. While traditional methods use image priors as constraints, modern deep learning methods use supervised learning with ground truth images to learn image features and priors. However, in some cases, ground truth images are not available, making supervised learning impractical. Recent data-centric learning frameworks such as …

Toward Building An Intelligent And Secure Network: An Internet Traffic Forecasting Perspective, Sajal Saha

Electronic Thesis and Dissertation Repository

Internet traffic forecast is a crucial component for the proactive management of self-organizing networks (SON) to ensure better Quality of Service (QoS) and Quality of Experience (QoE). Given the volatile and random nature of traffic data, this forecasting influences strategic development and investment decisions in the Internet Service Provider (ISP) industry. Modern machine learning algorithms have shown potential in dealing with complex Internet traffic prediction tasks, yet challenges persist. This thesis systematically explores these issues over five empirical studies conducted in the past three years, focusing on four key research questions: How do outlier data samples impact prediction accuracy for …

Classification Of Ddos Attack With Machine Learning Architectures And Exploratory Analysis, Amreen Anbar

Electronic Thesis and Dissertation Repository

The ever-increasing frequency of occurrence and sophistication of DDoS attacks pose a serious threat to network security. Accurate classification of DDoS attacks with efficiency is crucial in order to develop effective defense mechanisms. In this thesis, we propose a novel approach for DDoS classification using the CatBoost algorithm, on CICDDoS2019, a benchmark dataset containing 12 variations of DDoS attacks and legitimate traffic using real-world traffic traces. With a developed ensemble feature selection method and feature engineering, our model proves to be a good fit for DDoS attack type prediction. Our experimental results demonstrate that our proposed approach achieves high classification …

Generalizable Deep-Learning-Based Wireless Indoor Localization, Ali Owfi

All Theses

The growing interest in indoor localization has been driven by its wide range of applications in areas such as smart homes, industrial automation, and healthcare. With the increasing reliance on wireless devices for location-based services, accurate estimation of device positions within indoor environments has become crucial. Deep learning approaches have shown promise in leveraging wireless parameters like Channel State Information (CSI) and Received Signal Strength Indicator (RSSI) to achieve precise localization. However, despite their success in achieving high accuracy, these deep learning models suffer from limited generalizability, making them unsuitable for deployment in new or dynamic environments without retraining. To …

Adversarial Deep Learning And Security With A Hardware Perspective, Joseph Clements

All Dissertations

Adversarial deep learning is the field of study which analyzes deep learning in the presence of adversarial entities. This entails understanding the capabilities, objectives, and attack scenarios available to the adversary to develop defensive mechanisms and avenues of robustness available to the benign parties. Understanding this facet of deep learning helps us improve the safety of the deep learning systems against external threats from adversaries. However, of equal importance, this perspective also helps the industry understand and respond to critical failures in the technology. The expectation of future success has driven significant interest in developing this technology broadly. Adversarial deep …

Improving Inference Speed Of Perception Systems In Autonomous Unmanned Ground Vehicles, Bradley Selee

All Theses

Autonomous vehicle (AV) development has become one of the largest research challenges in businesses and research institutions. While much research has been done, autonomous driving still requires extensive amounts of research due to its immense, multi-factorial difficulty. Autonomous vehicles rely on many complex systems to function, make accurate decisions, and, above all, provide maximum safety. One of the most crucial components of autonomous driving is the perception system.

The perception system allows the vehicle to identify its surroundings and make accurate, but safe, decisions through the use of computer vision techniques like object detection, image segmentation, and path planning. Due …

Deep Learning Methods For Prediction Of And Escape From Protein Recognition, Bowen Dai

Dartmouth College Ph.D Dissertations

Protein interactions drive diverse processes essential to living organisms, and thus numerous biomedical applications center on understanding, predicting, and designing how proteins recognize their partners. While unfortunately the number of interactions of interest still vastly exceeds the capabilities of experimental determination methods, computational methods promise to fill the gap. My thesis pursues the development and application of computational methods for several protein interaction prediction and design tasks. First, to improve protein-glycan interaction specificity prediction, I developed GlyBERT, which learns biologically relevant glycan representations encapsulating the components most important for glycan recognition within their structures. GlyBERT encodes glycans with a branched …

A Flexible Photonic Reduction Network Architecture For Spatial Gemm Accelerators For Deep Learning, Bobby Bose

Theses and Dissertations--Electrical and Computer Engineering

As deep neural network (DNN) models increase significantly in complexity and size, it has become important to increase the computing capability of specialized hardware architectures typically used for DNN processing. The major linear operations of DNNs, which comprise the fully connected and convolution layers, are commonly converted into general matrix-matrix multiplication (GEMM) operations for acceleration. Specialized GEMM accelerators are typically employed to implement these GEMM operations, where a GEMM operation is decomposed into multiple vector-dot-product operations that run in parallel. A common challenge that arises in modern DNNs is the mismatch between the matrices used for GEMM operations and the …

Deep Learning-Based Intrusion Detection Methods For Computer Networks And Privacy-Preserving Authentication Method For Vehicular Ad Hoc Networks, Ayesha Dina

Theses and Dissertations--Computer Science

The incidence of computer network intrusions has significantly increased over the last decade, partially attributed to a thriving underground cyber-crime economy and the widespread availability of advanced tools for launching such attacks. To counter these attacks, researchers in both academia and industry have turned to machine learning (ML) techniques to develop Intrusion Detection Systems (IDSes) for computer networks. However, many of the datasets use to train ML classifiers for detecting intrusions are not balanced, with some classes having fewer samples than others. This can result in ML classifiers producing suboptimal results. In this dissertation, we address this issue and present …

Spatio-Temporal Deep Learning Approaches For Addressing Track Association Problem Using Automatic Identification System (Ais) Data, Md Asif Bin Syed

Graduate Theses, Dissertations, and Problem Reports

In the realm of marine surveillance, track association constitutes a pivotal yet challenging task, involving the identification and tracking of unlabelled vessel trajectories. The need for accurate data association algorithms stems from the urge to spot unusual vessel movements or threat detection. These algorithms link sequential observations containing location and motion information to specific moving objects, helping to build their real-time trajectories. These threat detection algorithms will be useful when a vessel attempts to conceal its identity. The algorithm can then identify and track the specific vessel from its incoming signal. The data for this study is sourced from the …

Optimized Learning Using Fuzzy-Inference-Assisted Algorithms For Deep Learning, Miroslava Barua

Open Access Theses & Dissertations

For years, researchers in Artificial Intelligence (AI) and Deep Learning (DL) observed that performance of a Deep Learning Network (DLN) could be improved by using larger and larger datasets coupled with complex network architectures. Although these strategies yield remarkable results, they have limits, dictated by data quantity and quality, rising costs by the increased computational power, or, more frequently, by long training times on networks that are very large. Training DLN requires laborious work involving multiple layers of densely connected neurons, updates to millions of network parameters, while potentially iterating thousands of times through millions of entries in a big …

Intelligent Autonomous Inspections Using Deep Learning And Detection Markers, Alejandro Martinez Acosta

Open Access Theses & Dissertations

Inspection of industrial and scientific facilities is a crucial task that must be performed regularly. These inspections tasks ensure that the facilityâ??s structure is in safe operational conditions for humans. Furthermore,the safe operation of industrial machinery, is dependent on the conditions of the environment. For safety reasons, inspections for both structural integrity and equipment is often manually performed by operators or technicians. Naturally, this is often a tedious and laborious task. Additionally, buildings and structures frequently contain hard to reach or dangerous areas, which leads to the harm, injury or death of humans. Autonomous robotic systems offer an attractive solution …

Lung Cancer Type Classification, Mohit Ramajibhai Ankoliya

Electronic Theses, Projects, and Dissertations

Lung cancer is the third most common cancer in the U.S. This research focuses on classifying lung cancer cells based on their tumor cell, shape, and biological traits in images automatically obtained by passing through the

convolutional layers. Additionally, I classify whether the lung cell is adenocarcinoma, large cell carcinoma, squamous cell carcinoma, or normal cell carcinoma. The benefit of this classification is an accurate prognosis, leading to patients receiving proper therapy. The Lung Cancer CT(Computed Tomography) image dataset from Kaggle has been drawn with 1000 CT images of various types of lung cancer. Two state-of-the-art convolutional neural networks (CNNs) …

Panodepth – Panoramic Monocular Depth Perception Model And Framework, Adley K. Wong

Master's Theses

Depth perception has become a heavily researched area as companies and researchers are striving towards the development of self-driving cars. Self-driving cars rely on perceiving the surrounding area, which heavily depends on technology capable of providing the system with depth perception capabilities. In this paper, we explore developing a single camera (monocular) depth prediction model that is trained on panoramic depth images. Our model makes novel use of transfer learning efficient encoder models, pre-training on a larger dataset of flat depth images, and optimizing the model for use with a Jetson Nano. Additionally, we present a training and optimization framework …

Generative Spatio-Temporal And Multimodal Analysis Of Neonatal Pain, Md Sirajus Salekin

USF Tampa Graduate Theses and Dissertations

Neonates can not express their pain like an adult person. Due to the lacking of proper muscle growth and inability to express non-verbally, it is difficult to understand their emotional status. In addition, if the neonates are under any treatment or left monitored after any major surgeries (post-operative), it is more difficult to understand their pain due to the side effect of medications and the caring system (i.e. intubated, masked face, covered body with blanket, etc.). In a clinical environment, usually, bedside nurses routinely observe the neonate and measure the pain status following any standard clinical pain scale. But current …

Applied Deep Learning: Case Studies In Computer Vision And Natural Language Processing, Md Reshad Ul Hoque

Electrical & Computer Engineering Theses & Dissertations

Deep learning has proved to be successful for many computer vision and natural language processing applications. In this dissertation, three studies have been conducted to show the efficacy of deep learning models for computer vision and natural language processing. In the first study, an efficient deep learning model was proposed for seagrass scar detection in multispectral images which produced robust, accurate scars mappings. In the second study, an arithmetic deep learning model was developed to fuse multi-spectral images collected at different times with different resolutions to generate high-resolution images for downstream tasks including change detection, object detection, and land cover …

Application Of Deep Learning For Medical Sciences And Epidemiology Data Analysis And Diagnostic Modeling, Somenath Chakraborty

Dissertations

Machine Learning and Artificial Intelligence have made significant progress concurrent with new advancements in hardware and software technologies. Deep learning methods heavily utilize parallel computing and Graphical Processing Units(GPU). It is already used in many applications ranging from image classification, object detection, segmentation, cyber security problems and others. Deep Learning is emerging as a viable choice in dealing with today’s real-time medical problems. We need new methods and technologies in the field of Medical Science and Epidemiology for detecting and diagnosing emerging threats from new viruses such as COVID-19. The use of Artificial Intelligence in these domains is becoming more …

Deep Learning For Load Forecasting With Smart Meter Data: Online And Federated Learning, Mohammad Navid Fekri

Electronic Thesis and Dissertation Repository

Electricity load forecasting has been attracting increasing attention because of its importance for energy management, infrastructure planning, and budgeting. In recent years, the proliferation of smart meters has created new opportunities for forecasting on the building and even individual household levels. Machine learning (ML) has achieved great successes in this domain; however, conventional ML techniques require data transfer to a centralized location for model training, therefore, increasing network traffic and exposing data to privacy and security risks. Also, traditional approaches employ offline learning, which means that they are only trained once and miss out on the possibility to learn from …

Quadratic Neural Network Architecture As Evaluated Relative To Conventional Neural Network Architecture, Reid Taylor

Senior Theses

Current work in the field of deep learning and neural networks revolves around several variations of the same mathematical model for associative learning. These variations, while significant and exceptionally applicable in the real world, fail to push the limits of modern computational prowess. This research does just that: by leveraging high order tensors in place of 2nd order tensors, quadratic neural networks can be developed and can allow for substantially more complex machine learning models which allow for self-interactions of collected and analyzed data. This research shows the theorization and development of mathematical model necessary for such an idea to …

Learning Representations For Human Identification, Sinan Sabri

Graduate Theses, Dissertations, and Problem Reports

Long-duration visual tracking of people requires the ability to link track snippets (a.k.a. tracklets) based on the identity of people. In lack of the availability of motion priors or hard biometrics (e.g., face, fingerprint, or iris), the common practice is to leverage soft biometrics for matching tracklets corresponding to the same person in different sightings. A common choice is to use the whole-body visual appearance of the person, as determined by the clothing, which is assumed to not change during tracking. The problem is challenging because distinct images of the same person may look very different, since no restrictions are …

Improving Feature Learning Capability And Interpretability Of Unsupervised Neural Networks, Chathurika S. Wickramasinghe Brahmana

Theses and Dissertations

The motivation for this dissertation is two-prong. Firstly, the current state of machine learning imposes the need for unsupervised Machine Learning (ML). Secondly, once such models are developed, a deeper understanding of ML models is necessary for humans to adapt and use such models.

Real-world systems generate massive amounts of unlabeled data at rapid speed, limiting the usability of state-of-the-art supervised machine learning approaches. Further, the manual labeling process is expensive, time-consuming, and requires the expertise of the data. Therefore, the existing supervised learning algorithms are unable to take advantage of the abundance of real-world unlabeled data. Thus, relying on …

Computer Vision Based Classification Of Fruits And Vegetables For Self-Checkout At Supermarkets, Khurram Hameed

Theses: Doctorates and Masters

The field of machine learning, and, in particular, methods to improve the capability of machines to perform a wider variety of generalised tasks are among the most rapidly growing research areas in today’s world. The current applications of machine learning and artificial intelligence can be divided into many significant fields namely computer vision, data sciences, real time analytics and Natural Language Processing (NLP). All these applications are being used to help computer based systems to operate more usefully in everyday contexts. Computer vision research is currently active in a wide range of areas such as the development of autonomous vehicles, …

Multimodal Adversarial Learning, Uche Osahor

Graduate Theses, Dissertations, and Problem Reports

Deep Convolutional Neural Networks (DCNN) have proven to be an exceptional tool for object recognition, generative modelling, and multi-modal learning in various computer vision applications. However, recent findings have shown that such state-of-the-art models can be easily deceived by inserting slight imperceptible perturbations to key pixels in the input. A good target detection systems can accurately identify targets by localizing their coordinates on the input image of interest. This is ideally achieved by labeling each pixel in an image as a background or a potential target pixel. However, prior research still confirms that such state of the art targets models …

Novel Natural Language Processing Models For Medical Terms And Symptoms Detection In Twitter, Farahnaz Golrooy Motlagh

Browse all Theses and Dissertations

This dissertation focuses on disambiguation of language use on Twitter about drug use, consumption types of drugs, drug legalization, ontology-enhanced approaches, and prediction analysis of data-driven by developing novel NLP models. Three technical aims comprise this work: (a) leveraging pattern recognition techniques to improve the quality and quantity of crawled Twitter posts related to drug abuse; (b) using an expert-curated, domain-specific DsOn ontology model that improve knowledge extraction in the form of drug-to-symptom and drug-to-side effect relations; and (c) modeling the prediction of public perception of the drug’s legalization and the sentiment analysis of drug consumption on Twitter. We collected …

Design Of Plastic Contaminant Eliminator In Seed Cotton, Joshua H. Tandio

Theses and Dissertations

Plastic contamination in cotton is a problem in cotton industry and researchers have worked on this problem with different approaches. This thesis documents the design of mechanical and electronic real-time systems for detecting and removing plastic contaminants. The mechanical system was designed to expose plastic embedded inside the seed cotton to the sensor and to separate plastic contaminated cotton from the process stream. The detection system consisted of an embedded computer interfaced with a USB camera and Neural Network (NN) software running in it. Two NN models were tested, a transfer learning model and a built-from-scratch original model. The original …