Engineering Commons^™

Self-Driving Toy Car Using Deep Learning, Fahim Ahmed, Suleyman Turac, Mubtasem Ali

Publications and Research

Our research focuses on building a student affordable platform for scale model self-driving cars. The goal of this project is to explore current developments of Open Source hardware and software to build a low-cost platform consisting of the car chassis/framework, sensors, and software for the autopilot. Our research will allow other students with low budget to enter into the world of Deep Learning, self-driving cars, and autonomous cars racing competitions.

Domain Adaptation In Unmanned Aerial Vehicles Landing Using Reinforcement Learning, Pedro Lucas Franca Albuquerque

Department of Computer Science and Engineering: Dissertations, Theses, and Student Research

Landing an unmanned aerial vehicle (UAV) on a moving platform is a challenging task that often requires exact models of the UAV dynamics, platform characteristics, and environmental conditions. In this thesis, we present and investigate three different machine learning approaches with varying levels of domain knowledge: dynamics randomization, universal policy with system identification, and reinforcement learning with no parameter variation. We first train the policies in simulation, then perform experiments both in simulation, making variations of the system dynamics with wind and friction coefficient, then perform experiments in a real robot system with wind variation. We initially expected that providing …

Pixel-Level Deep Multi-Dimensional Embeddings For Homogeneous Multiple Object Tracking, Mateusz Mittek

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

The goal of Multiple Object Tracking (MOT) is to locate multiple objects and keep track of their individual identities and trajectories given a sequence of (video) frames. A popular approach to MOT is tracking by detection consisting of two processing components: detection (identification of objects of interest in individual frames) and data association (connecting data from multiple frames). This work addresses the detection component by introducing a method based on semantic instance segmentation, i.e., assigning labels to all visible pixels such that they are unique among different instances. Modern tracking methods often built around Convolutional Neural Networks (CNNs) and additional, …

Data Analytics And Machine Learning To Enhance The Operational Visibility And Situation Awareness Of Smart Grid High Penetration Photovoltaic Systems, Aditya Sundararajan

FIU Electronic Theses and Dissertations

Electric utilities have limited operational visibility and situation awareness over grid-tied distributed photovoltaic systems (PV). This will pose a risk to grid stability when the PV penetration into a given feeder exceeds 60% of its peak or minimum daytime load. Third-party service providers offer only real-time monitoring but not accurate insights into system performance and prediction of productions. PV systems also increase the attack surface of distribution networks since they are not under the direct supervision and control of the utility security analysts.

Six key objectives were successfully achieved to enhance PV operational visibility and situation awareness: (1) conceptual cybersecurity …

Asap: A Source Code Authorship Program, Matthew F. Tennyson Phd

Faculty & Staff Research and Creative Activity

Source code authorship attribution is the task of determining who wrote a computer program, based on its source code, usually when the author is either unknown or under dispute. Areas where this can be applied include software forensics, cases of software copyright infringement, and detecting plagiarism. Numerous methods of source code authorship attribution have been proposed and studied. However, there are no known easily accessible and user-friendly programs that perform this task. Instead, researchers typically develop software in an ad hoc manner for use in their studies, and the software is rarely made publicly available. In this paper, we present …

A Hardware-Assisted Insider Threat Detection And Prevention Framework, Kyle W. Denney

FIU Electronic Theses and Dissertations

Today, the USB protocol is among the most widely used protocols. However, the mass-proliferation of USB has led to a threat vector wherein USB devices are assumed innocent, leaving computers open to an attack. Malicious USB devices can disguise themselves as benign devices to insert malicious commands to connected end devices. A rogue device appears benign to the average OS, requiring advanced detection schemes to identify malicious devices. However, using system-level hooks, advanced threats may subvert OS-reliant detection schemes. This thesis showcases USB-Watch, a hardware-based USB threat detection framework. The hardware can collect live USB traffic before the data can …

Sparse General Non-Negative Matrix Factorization Based On Left Semi-Tensor Product, Zigang Chen, Lixiang Li, Haipeng Peng, Yuhong Liu, Haihua Zhu, Yixian Yang

Computer Science and Engineering

The dimension reduction of large scale high-dimensional data is a challenging task, especially the dimension reduction of face data and the accuracy increment of face recognition in the large scale face recognition system, which may cause large storage space and long recognition time. In order to further reduce the recognition time and the storage space in the large scale face recognition systems, on the basis of the general non-negative matrix factorization based on left semi-tensor (GNMFL) without dimension matching constraints proposed in our previous work, we propose a sparse GNMFL/L (SGNMFL/L) to decompose a large number of face data sets …

Depressiongnn: Depression Prediction Using Graph Neural Network On Smartphone And Wearable Sensors, Param Bidja

Honors Scholar Theses

Depression prediction is a complicated classification problem because depression diagnosis involves many different social, physical, and mental signals. Traditional classification algorithms can only reach an accuracy of no more than 70% given the complexities of depression. However, a novel approach using Graph Neural Networks (GNN) can be used to reach over 80% accuracy, if a graph can represent the depression data set to capture differentiating features. Building such a graph requires 1) the definition of node features, which must be highly correlated with depression, and 2) the definition for edge metrics, which must also be highly correlated with depression. In …

Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods

Undergraduate Research & Mentoring Program

In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the evaluation of …

Computational Modeling Of Trust Factors Using Reinforcement Learning, C. M. Kuzio, A. Dinh, C. Stone, L. Vidyaratne, K. M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

As machine-learning algorithms continue to expand their scope and approach more ambiguous goals, they may be required to make decisions based on data that is often incomplete, imprecise, and uncertain. The capabilities of these models must, in turn, evolve to meet the increasingly complex challenges associated with the deployment and integration of intelligent systems into modern society. Historical variability in the performance of traditional machine-learning models in dynamic environments leads to ambiguity of trust in decisions made by such algorithms. Consequently, the objective of this work is to develop a novel computational model that effectively quantifies the reliability of autonomous …

Identifying Key Topics Bearing Negative Sentiment On Twitter: Insights Concerning The 2015-2016 Zika Epidemic, Ravali Mamidi, Michele Miller, Tanvi Banerjee, William Romine, Amit Sheth

Publications

Background To understand the public sentiment regarding the Zika virus, social media can be leveraged to understand how positive, negative, and neutral sentiments are expressed in society. Specifically, understanding the characteristics of negative sentiment could help inform federal disease control agencies’ efforts to disseminate relevant information to the public about Zika-related issues.

Objective The purpose of this study was to analyze the public sentiment concerning Zika using posts on Twitter and determine the qualitative characteristics of positive, negative, and neutral sentiments expressed.

Methods Machine learning techniques and algorithms were used to analyze the sentiment of tweets concerning Zika. A supervised …

Predicting Cascading Failures In Power Grids Using Machine Learning Algorithms, Rezoan Ahmed Shuvro, Pankaz Das, Majeed M. Hayat, Mitun Talukder

Electrical and Computer Engineering Faculty Research and Publications

Although there has been notable progress in modeling cascading failures in power grids, few works included using machine learning algorithms. In this paper, cascading failures that lead to massive blackouts in power grids are predicted and classified into no, small, and large cascades using machine learning algorithms. Cascading-failure data is generated using a cascading failure simulator framework developed earlier. The data set includes the power grid operating parameters such as loading level, level of load shedding, the capacity of the failed lines, and the topological parameters such as edge betweenness centrality and the average shortest distance for numerous combinations of …

Transparency And Algorithmic Governance, Cary Coglianese, David Lehr

All Faculty Scholarship

Machine-learning algorithms are improving and automating important functions in medicine, transportation, and business. Government officials have also started to take notice of the accuracy and speed that such algorithms provide, increasingly relying on them to aid with consequential public-sector functions, including tax administration, regulatory oversight, and benefits administration. Despite machine-learning algorithms’ superior predictive power over conventional analytic tools, algorithmic forecasts are difficult to understand and explain. Machine learning’s “black-box” nature has thus raised concern: Can algorithmic governance be squared with legal principles of governmental transparency? We analyze this question and conclude that machine-learning algorithms’ relative inscrutability does not pose a …

Analyzing Twitter Feeds To Facilitate Crises Informatics And Disaster Response During Mass Emergencies, Arshdeep Kaur

Dissertations

It is a common practice these days for general public to use various micro-blogging platforms, predominantly Twitter, to share ideas, opinions and information about things and life. Twitter is also being increasingly used as a popular source of information sharing during natural disasters and mass emergencies to update and communicate the extent of the geographic phenomena, report the affected population and casualties, request or provide volunteering services and to share the status of disaster recovery process initiated by humanitarian-aid and disaster-management organizations. Recent research in this area has affirmed the potential use of such social media data for various disaster …