Engineering Commons^™

An Adaptive Multiple-Object Tracking Architecture For Long-Duration Videos With Variable Target Density, Joachim Lohn-Jaramillo

Dartmouth College Ph.D Dissertations

Multiple-Object Tracking (MOT) methods are used to detect targets in individual video frames, e.g., vehicles, people, and other objects, and then record each unique target’s path over time. Current state-of-the-art approaches are extremely complex because most rely on extracting and comparing visual features at every frame to track each object. These approaches are geared toward high-difficulty-tracking scenarios, e.g., crowded airports, and require expensive dedicated hardware, e.g., Graphics Processing Units. In hardware-constrained applications, researchers are turning to older, less complex MOT methods, which reveals a serious scalability issue within the state-of-the-art. Crowded environments are a niche application for MOT, i.e., there …

Instance Segmentation-Based Depth Completion Using Sensor Fusion And Adaptive Clustering For Autonomous Vehicle Perception, Mohammad Z. El-Yabroudi

Dissertations

Depth sensing is critical for safe and accurate maneuvering in robotics and self-driving car (SDC) applications. Most recent LiDAR sensors, such as Ouster and Velodyne, offer 360 degrees of scanning at the rate of ten frames per second, making them very appropriate for autonomous driving applications. However, LiDAR point cloud data show many shortcomings, especially its data sparsity and unassigned nature, making it very challenging to utilize in applications such as perception, 3D object detection, 3D scene reconstruction, and simultaneous localization and mapping.

In this study, a novel framework using instance image segmentation and the raw LiDAR data for the …

Machine Learning Based Real-Time Quantification Of Production From Individual Clusters In Shale Wells, Ayodeji Luke Aboaba

Graduate Theses, Dissertations, and Problem Reports

Over the last two decades, there has been advances in downhole monitoring in oil and gas wells with the use of Fiber-Optic sensing technology such as the Distributed Temperature Sensing (DTS). Unlike a conventional production log that provides only snapshots of the well performance, DTS provides continuous temperature measurements along the entire wellbore.

Whether by fluid extraction or injection, oil and gas production changes reservoir conditions, and continuous monitoring of downhole conditions is highly desirable. This research study presents a tool for real-time quantification of production from individual perforation clusters in a multi-stage shale well using Artificial Intelligence and Machine …

Topological Hierarchies And Decomposition: From Clustering To Persistence, Kyle A. Brown

Browse all Theses and Dissertations

Hierarchical clustering is a class of algorithms commonly used in exploratory data analysis (EDA) and supervised learning. However, they suffer from some drawbacks, including the difficulty of interpreting the resulting dendrogram, arbitrariness in the choice of cut to obtain a flat clustering, and the lack of an obvious way of comparing individual clusters. In this dissertation, we develop the notion of a topological hierarchy on recursively-defined subsets of a metric space. We look to the field of topological data analysis (TDA) for the mathematical background to associate topological structures such as simplicial complexes and maps of covers to clusters in …

Situation-Aware Quality Of Service Enhancement For Heterogeneous Ultra-Dense Wireless Iot Networks, Sabin Bhandari

Electronic Thesis and Dissertation Repository

By engaging a massive number of heterogeneous devices, future Internet of Things (IoT) systems are expected to support diverse applications ranging from eHealthcare to industrial control. In highly-dense deployment scenarios such as Industrial IoT (IIoT) systems, meeting the stringent Quality of Service (QoS) requirements such as low-latency and high reliability becomes challenging due to the uncertainty and dynamics within the IoT networks. To enhance the overall QoS performance, this thesis aims to address the technical challenges of IoT networks. Firstly, to enhance the network reliability, a cloud-assisted priority-based channel access and data aggregation scheme is proposed to minimize the network …

Constructing Frameworks For Task-Optimized Visualizations, Ghulam Jilani Abdul Rahim Quadri

USF Tampa Graduate Theses and Dissertations

Visualization is crucial in today’s data-driven world to augment and enhance human understanding and decision-making. Effective visualizations must support accuracy in visual task performance and expressive data communication. Effective visualization design depends on the visual channels used, chart types, or visual tasks. However, design choices and visual judgment are co-related, and effectiveness is not one-dimensional, leading to a significant need to understand the intersection of these factors to create optimized visualizations. Hence, constructing frameworks that consider both design decisions and the task being performed enables optimizing visualization design to maximize efficacy. This dissertation describes experiments, techniques, and user studies to …

Efficient Yet Robust Privacy For Video Streaming, Luke Cranfill, Junggab Son

Master of Science in Computer Science Theses

MPEG-DASH is a video streaming standard that outlines protocols for sending audio and video content from a server to a client over HTTP. The standard has been widely utilized by the video streaming industry. However, it creates an opportunity for an adversary to invade users’ privacy. While a user is watching a video, information is leaked in the form of meta-data, the size and time that the server sent data to the user. This information is not protected by encryption and can be used to create a fingerprint for a video. Once the fingerprint is created, the adversary can use …

Analyzing Freight Congestion And Transportation Performance Measures Using The National Performance Management Research Data Set (Npmrds), Yaxin Zhang

Dissertations and Theses

Traffic congestion is common in urban areas. It results in loss of productivity, increased risk of passenger safety, increased fuel consumption, environment pollution, etc. Improving performance measurement is a tool to improve traffic flow and capacity planning.

The main data source in this research is the National Performance Management Research Data Set (NPMRDS) for 2018. NPMRDS is a form of commercial GPS probe data, obtained from vehicles with on-board probe technologies. This dataset is licensed by the Federal Highway Administration and is made available to State Departments of Transportation (DOTs) and Metropolitan Planning Organizations (MPOs) for the purpose of federally …

A Fuzzy Clustering Methodology To Analyze Interfaces And Assess Integration Risks In Large-Scale Systems, Josh Henry Goldschmid

Doctoral Dissertations

“Interface analysis and integration risk assessment for a large-scale, complex system is a difficult systems engineering task, but critical to the success of engineering systems with extraordinary capabilities. When dealing with large-scale systems there is little time for data gathering and often the analysis can be overwhelmed by unknowns and sometimes important factors are not measurable because of the complexities of the interconnections within the system. This research examines the significance of interface analysis and management, identifies weaknesses in literature on risk assessment for a complex system, and exploits the benefits of soft computing approaches in the interface analysis in …

Texture-Driven Image Clustering In Laser Powder Bed Fusion, Alexander H. Groeger

Browse all Theses and Dissertations

The additive manufacturing (AM) field is striving to identify anomalies in laser powder bed fusion (LPBF) using multi-sensor in-process monitoring paired with machine learning (ML). In-process monitoring can reveal the presence of anomalies but creating a ML classifier requires labeled data. The present work approaches this problem by printing hundreds of Inconel-718 coupons with different processing parameters to capture a wide range of process monitoring imagery with multiple sensor types. Afterwards, the process monitoring images are encoded into feature vectors and clustered to isolate groups in each sensor modality. Four texture representations were learned by training two convolutional neural network …

Texture-Driven Image Clustering In Laser Powder Bed Fusion, Alexander H. Groeger

Browse all Theses and Dissertations

The additive manufacturing (AM) field is striving to identify anomalies in laser powder bed fusion (LPBF) using multi-sensor in-process monitoring paired with machine learning (ML). In-process monitoring can reveal the presence of anomalies but creating a ML classifier requires labeled data. The present work approaches this problem by printing hundreds of Inconel-718 coupons with different processing parameters to capture a wide range of process monitoring imagery with multiple sensor types. Afterwards, the process monitoring images are encoded into feature vectors and clustered to isolate groups in each sensor modality. Four texture representations were learned by training two convolutional neural network …

Optimizing Cluster Sets For The Scan Statistic Using Local Search, James Shulgan

Graduate Research Theses & Dissertations

In recent years, scattering sensors to produce wireless sensor networks (WSN) has been proposed for detecting localized events in large areas. Because sensor measurements are noisy, the WSN needs to use statistical methods such as the scan statistic. The scan statistic groups measurements into various clusters, computes a cluster statistic for each cluster, and decides that an event has happened if any of the statistics exceeds a threshold. Previous researchers have investigated the performance of the scan statistic to detect events; however, little attention was given to the optimization of which clusters the scan statistic should use. Using the scan …

Lane Detection Of Autonomous Vehicles Using Clustering And Augmented Sliding Windows Techniques, Keerti Chand Bhupathi

Graduate Research Theses & Dissertations

In this thesis, detection of solid lines and dashed lines of lanes using augmented sliding window technique, clustering technique and combination of both augmented sliding window and clustering is discussed. The lane points are extracted using image processing techniques. The performance of lane detection using these techniques is analyzed. Lanes are simulated in a laboratory for the input data set. The input data set consists of curved lines of dashed and solid lines which split and merge. Further, partially obscured lanes are also tested with the algorithm. The center of the lanes from vehicle to horizon is found based on …

Development Of A Modeling Algorithm To Predict Lean Implementation Success, Richard Charles Barclay

Doctoral Dissertations

”Lean has become a common term and goal in organizations throughout the world. The approach of eliminating waste and continuous improvement may seem simple on the surface but can be more complex when it comes to implementation. Some firms implement lean with great success, getting complete organizational buy-in and realizing the efficiencies foundational to lean. Other organizations struggle to implement lean. Never able to get the buy-in or traction needed to really institute the sort of cultural change that is often needed to implement change. It would be beneficial to have a tool that organizations could use to assess their …

An Approach To Cluster And Benchmark Regional Emergency Medical Service Agencies, Swetha Kondapalli

Browse all Theses and Dissertations

Emergency Medical Service (EMS) providers are the first responders for an injured patient on the field. Their assessment of patient injuries and determination of an appropriate hospital play a critical role in patient outcomes. A majority of states in the US have established a state-level governing body (e.g., EMS Division) that is responsible for developing and maintaining a robust EMS system throughout the state. Such divisions develop standards, accredit EMS agencies, oversee the trauma system, and support new initiatives through grants and training. But to do so, these divisions require data to enable them to first understand the similarities between …

Online Clustering With Bayesian Nonparametrics, Matthew D. Scherreik

Browse all Theses and Dissertations

Clustering algorithms, such as Gaussian mixture models and K-means, often require the number of clusters to be specified a priori. Bayesian nonparametric (BNP) methods avoid this problem by specifying a prior distribution over the cluster assignments that allows the number of clusters to be inferred from the data. This can be especially useful for online clustering tasks, where data arrives in a continuous stream and the number of clusters may dynamically change over time. Classical BNP priors often overestimate the number of clusters, however, leading researchers to develop new priors with more control over this tendency. To date, BNP algorithms …

An Application Of Clustering And Cluster Update Methods To Boiler Sensor Prediction And Case-Based-Reasoning To Boiler Repair, Timothy Edward Rooney

Theses and Dissertations

Driven by demand from both consumers and manufacturers alike, Internet of Things (IoT)

capabilities are being built into more products. Consumers want more control and access to their

devices, while manufacturers can find data gathered from IoT-capable products invaluable. In

this thesis, we use data from a growing fleet of IoT-connected boilers in the residential, lightcommercial, and medium-commercial ranges to demonstrate a framework for cluster initialization

and updating. We compare two methods of dynamically updating clusters: a sequential method

inspired by sequential K-means clustering and a cohesion-based method called DYNC. A predictive

artificial neural network system demonstrates the effectiveness of …

Clustering Heterogeneous Autism Spectrum Disorder Data., Mariem Boujelbene

Electronic Theses and Dissertations

Autism spectrum disorder (ASD) is a developmental disorder that affects communication and behavior. Several studies have been conducted in the past years to develop a better understanding of the disease and therefore a better diagnosis and a better treatment by analyzing diverse data sets consisting of behavioral surveys and tests, phenotype description, and brain imagery. However, data analysis is challenged by the diversity, complexity and heterogeneity of patient cases and by the need for integrating diverse data sets to reach a better understanding of ASD. The aim of our study is to mine homogeneous groups of patients from a heterogeneous …

Supply Chain Network Analysis For Outboard Motors At Motor Boaters Usa, Seyedalireza (Ali) Ghiasi, Chase Griffith, Djanene Manuel, Yesenia Pérez, Alvand Rafiee

Senior Design Project For Engineers

Motor Boaters USA found themselves possibly spending too much on their current network distribution of small and large outboard motors and requested new distribution alternatives for the U.S. Through past network distribution data analysis, the team devised 3 scenarios it believed would provide one or more cost effective distribution networks applicable to the request. Through what-if analysis, the teams' calculations produced solid results, which were then presented to Motor Boaters USA for reflection and possible implementation.

Modelo De Ruteo De Vehículos Para Disminuir Emisión De Material Particulado Generado Por Transporte De Carga: Empresa Del Sector Retail En Bogotá, Carolina Arévalo Alarcón, Rafael Antonio Rojas Romero

Ingeniería Industrial

En Colombia, la satisfacción de la demanda de productos básicos de la canasta familiar, así como de consumo personal, ha sido suplida en su mayoría por la industria retail. Nuevos formatos de venta como el “Hard Discount” han llegado al país, tales como D1, Ara y Justo y Bueno, que con una estrategia de expansión continua incrementan la oferta. Este formato de venta es sostenible cuando la oferta es constante, lo cual solo es posible con una planificación de distribución apropiada incrementando su complejidad. Esta planificación se puede asociar como un VRP donde están definidas ventanas de tiempo para el …

Building A Classification Model Using Affinity Propagation, Christopher R. Klecker

Electronic Theses and Dissertations

Regular classification of data includes a training set and test set. For example for Naïve Bayes, Artificial Neural Networks, and Support Vector Machines, each classifier employs the whole training set to train itself. This thesis will explore the possibility of using a condensed form of the training set in order to get a comparable classification accuracy. The technique explored in this thesis will use a clustering algorithm to explore with data records can be labeled as exemplar, or a quality of multiple records. For example, is it possible to compress say 50 records into one single record? Can a single …

Adaptive Identification Of Classification Decision Boundary Of Turbine Blade Mode Shape Under Geometric Uncertainty, Ian M. Boyd

Browse all Theses and Dissertations

Integrally Bladed Rotors (IBR) of aircraft turbine engines suffer from fluctuations in the dynamic response that occurs due to blade to blade geometric deviations. The Stochastic Approach for Blade and Rotor Emulation (SABRE) framework has been used to enable a probabilistic study of mistuned blades in which a reduced order modeling technique is applied in conjunction with sets of surrogate models, called emulators, to make predictions of mistuned mode shapes. SABRE has proven useful for non-switching mode shapes. However, switching mode shapes have non-stationary or discontinuous response surfaces which reduce the accuracy of the surrogate models used in SABRE. To …

Scalable Clustering For Immune Repertoire Sequence Analysis, Prem Bhusal

Browse all Theses and Dissertations

The development of the next-generation sequencing technology has enabled systems immunology researchers to conduct detailed immune repertoire analysis at the molecule level. Large sequence datasets (e.g., millions of sequences) are being collected to comprehensively understand how the immune system of a patient evolves over different stages of disease development. A recent study has shown that the hierarchical clustering (HC) algorithm gives the best results for B-cell clones analysis - an important type of immune repertoire sequencing (IR-Seq) analysis. However, due to the inherent complexity, the classical hierarchical clustering algorithm does not scale well to large sequence datasets. Surprisingly, no algorithms …

Neuroengineering Of Clustering Algorithms, Leonardo Enzo Brito Da Silva

Doctoral Dissertations

"Cluster analysis can be broadly divided into multivariate data visualization, clustering algorithms, and cluster validation. This dissertation contributes neural network-based techniques to perform all three unsupervised learning tasks. Particularly, the first paper provides a comprehensive review on adaptive resonance theory (ART) models for engineering applications and provides context for the four subsequent papers. These papers are devoted to enhancements of ART-based clustering algorithms from (a) a practical perspective by exploiting the visual assessment of cluster tendency (VAT) sorting algorithm as a preprocessor for ART offline training, thus mitigating ordering effects; and (b) an engineering perspective by designing a family of …

On Wlan Fingerprint Indoor Positioning Systems Clustering, And Classification For Enhanced Performance, Haider G. Al Glehawi

Masters Theses

The most economic and affordable IPS are those incorporating existing infrastructure, such as the widely spread Wireless Local Area Network (WLAN). The Received Signal Strength (RSS) fingerprinting-based system is one of the most promising and powerful techniques so far to be used for indoor positioning. However, there are two challenges in using RSS based IPS; the first challenge is the variation of RSS to indoor multipath propagation, and the second is the high number of Access Points (APs) that are deployed in the region of interest. The first issue leads to degradation in the performance of RSS based IPS, while …

Retail Data Analytics Using Graph Database, Rashmi Priya

Theses and Dissertations--Computer Science

Big data is an area focused on storing, processing and visualizing huge amount of data. Today data is growing faster than ever before. We need to find the right tools and applications and build an environment that can help us to obtain valuable insights from the data. Retail is one of the domains that collects huge amount of transaction data everyday. Retailers need to understand their customer’s purchasing pattern and behavior in order to take better business decisions.

Market basket analysis is a field in data mining, that is focused on discovering patterns in retail’s transaction data. Our goal is …

Interactive Clinical Event Pattern Mining And Visualization Using Insurance Claims Data, Zhenhui Piao

Theses and Dissertations--Computer Science

With exponential growth on a daily basis, there is potentially valuable information hidden in complex electronic medical records (EMR) systems. In this thesis, several efficient data mining algorithms were explored to discover hidden knowledge in insurance claims data. The first aim was to cluster three levels of information overload(IO) groups among chronic rheumatic disease (CRD) patient groups based on their clinical events extracted from insurance claims data. The second aim was to discover hidden patterns using three renowned pattern mining algorithms: Apriori, frequent pattern growth(FP-Growth), and sequential pattern discovery using equivalence classes(SPADE). The SPADE algorithm was found to be the …

Machine Learning Techniques Implementation In Power Optimization, Data Processing, And Bio-Medical Applications, Khalid Khairullah Mezied Al-Jabery

Doctoral Dissertations

"The rapid progress and development in machine-learning algorithms becomes a key factor in determining the future of humanity. These algorithms and techniques were utilized to solve a wide spectrum of problems extended from data mining and knowledge discovery to unsupervised learning and optimization. This dissertation consists of two study areas. The first area investigates the use of reinforcement learning and adaptive critic design algorithms in the field of power grid control. The second area in this dissertation, consisting of three papers, focuses on developing and applying clustering algorithms on biomedical data. The first paper presents a novel modelling approach for …

Offline And Online Density Estimation For Large High-Dimensional Data, Aref Majdara

Dissertations, Master's Theses and Master's Reports

Density estimation has wide applications in machine learning and data analysis techniques including clustering, classification, multimodality analysis, bump hunting and anomaly detection. In high-dimensional space, sparsity of data in local neighborhood makes many of parametric and nonparametric density estimation methods mostly inefficient.

This work presents development of computationally efficient algorithms for high-dimensional density estimation, based on Bayesian sequential partitioning (BSP). Copula transform is used to separate the estimation of marginal and joint densities, with the purpose of reducing the computational complexity and estimation error. Using this separation, a parallel implementation of the density estimation algorithm on a 4-core CPU is …

Graph-Based Latent Embedding, Annotation And Representation Learning In Neural Networks For Semi-Supervised And Unsupervised Settings, Ismail Ozsel Kilinc

USF Tampa Graduate Theses and Dissertations

Machine learning has been immensely successful in supervised learning with outstanding examples in major industrial applications such as voice and image recognition. Following these developments, the most recent research has now begun to focus primarily on algorithms which can exploit very large sets of unlabeled examples to reduce the amount of manually labeled data required for existing models to perform well. In this dissertation, we propose graph-based latent embedding/annotation/representation learning techniques in neural networks tailored for semi-supervised and unsupervised learning problems. Specifically, we propose a novel regularization technique called Graph-based Activity Regularization (GAR) and a novel output layer modification called …