Engineering Commons^™

Brain-Inspired Spatio-Temporal Learning With Application To Robotics, Thiago André Ferreira Medeiros

USF Tampa Graduate Theses and Dissertations

The human brain still has many mysteries and one of them is how it encodes information. The following study intends to unravel at least one such mechanism. For this it will be demonstrated how a set of specialized neurons may use spatial and temporal information to encode information. These neurons, called Place Cells, become active when the animal enters a place in the environment, allowing it to build a cognitive map of the environment. In a recent paper by Scleidorovich et al. in 2022, it was demonstrated that it was possible to differentiate between two sequences of activations of a …

Deep Learning Enhancement And Privacy-Preserving Deep Learning: A Data-Centric Approach, Hung S. Nguyen

USF Tampa Graduate Theses and Dissertations

Deep Learning and its applications have become attractive to a lot of research recentlybecause of its capability to capture important information from large amounts of data. While most of the work focuses on finding the best model parameters, improving machine learning performance from data perspective still needs more attention. In this work, we propose techniques to enhance the robustness of deep learning classification by tackling data issue. Specifically, our data processing proposals aim to alleviate the impacts of class-imbalanced data and non- IID data in deep learning classification and federated learning scenarios. In addition, data pre-processing strategies such that dimensionality …

Deep Reinforcement Learning Based Optimization Techniques For Energy And Socioeconomic Systems, Salman Sadiq Shuvo

USF Tampa Graduate Theses and Dissertations

Optimization, which refers to making the best or most out of a system, is critical for an organization's strategic planning. Optimization theories and techniques aim to find the optimal solution that maximizes/minimizes the values of an objective function within a set of constraints. Deep Reinforcement Learning (DRL) is a popular Machine Learning technique for optimization and resource allocation tasks. Unlike the supervised ML that trains on labeled data, DRL techniques require a simulated environment to capture the stochasticity of real-world complex systems. This uncertainty in future transitions makes the planning authorities doubt real-world implementation success. Furthermore, the DRL methods have …

Adaptive Multi-Scale Place Cell Representations And Replay For Spatial Navigation And Learning In Autonomous Robots, Pablo Scleidorovich

USF Tampa Graduate Theses and Dissertations

Place cells are one of the most widely studied neurons thought to play a vital role in spatial cognition. Extensive studies show that their activity in the rodent hippocampus is highly correlated with the animal’s spatial location, forming “place fields” of smaller sizes near the dorsal pole and larger sizes near the ventral pole. Despite advances, it is yet unclear how this multi-scale representation enables navigation in complex environments.

In this dissertation, we analyze the place cell representation from a computational point of view, evaluating how multi-scale place fields impact navigation in large and cluttered environments. The objectives are to …

Analyzing Decision-Making In Robot Soccer For Attacking Behaviors, Justin Rodney

USF Tampa Graduate Theses and Dissertations

In robotics soccer, decision-making is critical to the performance of a team’s SoftwareSystem. The University of South Florida’s (USF) RoboBulls team implements behavior for the robots by using traditional methods such as analytical geometry to path plan and determine whether an action should be taken. In recent works, Machine Learning (ML) and Reinforcement Learning (RL) techniques have been used to calculate the probability of success for a pass or goal, and even train models for performing low-level skills such as traveling towards a ball and shooting it towards the goal[1, 2]. Open-source frameworks have been created for training Reinforcement Learning …

Adaptive Network Slicing In Fog Ran For Iot With Heterogeneous Latency And Computing Requirements: A Deep Reinforcement Learning Approach, Almuthanna Nassar

USF Tampa Graduate Theses and Dissertations

In view of the recent advances in Internet of Things (IoT) devices and the emerging new breed of smart city applications and intelligent vehicular systems driven by artificial intelligence, fog radio access network (F-RAN) has been recently introduced for the next generation wireless communications. The capability of F-RAN has emerged to overcome the latency limitations of cloud-RAN (C-RAN) and assure the quality-of-service (QoS) requirements of the ultra-reliable-low-latency-communication (URLLC) for IoT applications. To this end, fog nodes (FNs) are equipped with computing, signal processing and storage capabilities to extend the inherent operations and services of the cloud to the edge. However, …

An Automated Framework For Connected Speech Evaluation Of Neurodegenerative Disease: A Case Study In Parkinson's Disease, Sai Bharadwaj Appakaya

USF Tampa Graduate Theses and Dissertations

Neurodegenerative diseases affect millions of people around the world. The progressive degeneration worsens the symptoms, heavily impacting the quality of life of the patients as well as the caregivers. Speech production is one of the physiological processes affected by neurodegenerative diseases like Alzheimer’s disease, amyotrophic lateral sclerosis (ALS) and Parkinson’s disease (PD). Speech is the most basic form of communication, and the effect of neurodegeneration degrades speech production, thereby reducing social interaction and mental well-being. PD is the second most common neurodegenerative disease affecting speech production in 90% of the diagnosed individuals. Speech analysis methods for PD in clinical methods …

Next-Generation Self-Organizing Communications Networks: Synergistic Application Of Machine Learning And User-Centric Technologies, Chetana V. Murudkar

USF Tampa Graduate Theses and Dissertations

The telecommunications industry is going through a metamorphic journey where the 5G and 6G technologies will be deeply rooted in the society forever altering how people access and use information. In support of this transformation, this dissertation proposes a fundamental paradigm shift in the design, performance assessment, and optimization of wireless communications networks developing the next-generation self-organizing communications networks with the synergistic application of machine learning and user-centric technologies.

This dissertation gives an overview of the concept of self-organizing networks (SONs), provides insight into the “hot” technology of machine learning (ML), and offers an intuitive understanding of the user-centric (UC) …

Action Recognition Using The Motion Taxonomy, Maxat Alibayev

USF Tampa Graduate Theses and Dissertations

In the last years, modern action recognition frameworks with deep architectures have achieved impressive results on the large-scale activity datasets. All state-of-the-art models share one common attribute: two-stream architectures. One deep model takes RGB frames, while the other model is fed with pre-computed optical flow vectors. The outputs of both models are combined to be used as a final probability distribution for the action classes. When comparing the results of individual models with the fused model, it is common to see that that latter method is more superior. Researchers explain that phenomena with the fact that optical flow vectors serve …

Artificial Intelligence Towards The Wireless Channel Modeling Communications In 5g, Saud Mobark Aldossari

USF Tampa Graduate Theses and Dissertations

Channel prediction is a mathematical predicting of the natural propagation of the signal that helps the receiver to approximate the affected signal, which plays an important role in highly mobile or dynamic channels. The standard wireless communication channel modeling can be facilitated by either deterministic or stochastic channel methodologies. The deterministic approach is based on the electromagnetic theories and every single object in that environment has to be known in that propagation space and an example of this method is ray tracing. While the stochastic modeling method is based on measurements that involve statistical distributions of the channel parameters and …

Functional Object-Oriented Network: A Knowledge Representation For Service Robotics, David Andrés Paulius Ramos

USF Tampa Graduate Theses and Dissertations

In this dissertation, we discuss our work behind the development of the functional object-oriented network (abbreviated as FOON), a graphical knowledge representation for robotic manipulation and understanding of its own actions and (potentially) the intentions of humans in the household. Based on the theory of affordance, this representation captures manipulations and their effects on actions through the coupling of object and motion nodes as fundamental learning units known as functional units. The activities currently represented in FOON are cooking related, but this representation can be extended to other activities that involve manipulation of objects which result in observable changes of …

Robotic Motion Generation By Using Spatial-Temporal Patterns From Human Demonstrations, Yongqiang Huang

USF Tampa Graduate Theses and Dissertations

Robots excel in manufacturing facilities because the tasks are repetitive and do not change. However, when the tasks change, which happens in almost all tasks that humans perform daily, such as cutting, pouring, and grasping, etc., robots perform much worse. We aim at teaching robots to perform tasks that are subject to change using demonstrations collected from humans, a problem referred to as learning from demonstration (LfD).

LfD consists of two parts: the data of human demonstrations, and the algorithm that extracts knowledge from the data to perform the same motions. Similarly, this thesis is divided into two parts. The …

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 …

Scene-Dependent Human Intention Recognition For An Assistive Robotic System, Kester Duncan

USF Tampa Graduate Theses and Dissertations

In order for assistive robots to collaborate effectively with humans for completing everyday tasks, they must be endowed with the ability to effectively perceive scenes and more importantly, recognize human intentions. As a result, we present in this dissertation a novel scene-dependent human-robot collaborative system capable of recognizing and learning human intentions based on scene objects, the actions that can be performed on them, and human interaction history. The aim of this system is to reduce the amount of human interactions necessary for communicating tasks to a robot. Accordingly, the system is partitioned into scene understanding and intention recognition modules. …

Robotic Swarming Without Inter-Agent Communication, Daniel Jonathan Standish

USF Tampa Graduate Theses and Dissertations

Many physical and algorithmic swarms utilize inter-agent communication to achieve advanced swarming behaviors. These swarms are inspired by biological swarms that can be seen throughout nature and include bee swarms, ant colonies, fish schools, and bird flocks. These biological swarms do not utilize inter-agent communication like their physical and algorithmic counterparts. Instead, organisms in nature rely on a local awareness of other swarm members that facilitates proper swarm motion and behavior. This research aims to pursue an effective swarm algorithm using only line-of-sight proximity information and no inter-agent communication. It is expected that the swarm performance will be lower than …

A Location-Aware Architecture Supporting Intelligent Real-Time Mobile Applications, Sean J. Barbeau

USF Tampa Graduate Theses and Dissertations

This dissertation presents LAISYC, a modular location-aware architecture for intelligent real-time mobile applications that is fully-implementable by third party mobile app developers and supports high-precision and high-accuracy positioning systems such as GPS. LAISYC significantly improves device battery life, provides location data authenticity, ensures security of location data, and significantly reduces the amount of data transferred between the phone and server. The design, implementation, and evaluation of LAISYC using real mobile phones include the following modules: the GPS Auto-Sleep module saves battery energy when using GPS, maintaining acceptable movement tracking (approximately 89% accuracy) with an approximate average doubling of battery life. …