Artificial Intelligence and Robotics Commons^™

S2cd: Self-Heuristic Speaker Content Disentanglement For Any-To-Any Voice Conversion, Pengfei Wei, Xiang Yin, Chunfeng Wang, Zhonghao Li, Xinghua Qu, Zhiqiang Xu, Zejun Ma

Machine Learning Faculty Publications

In this paper, we propose a Self-heuristic Speaker Content Disentanglement (S2CD) model for any to any voice conversion without using any external resources, e.g., speaker labels or vectors, linguistic models, and transcriptions. S2CD is built on the disentanglement sequential variational autoencoder (DSVAE), but improves DSVAE structure at the model architecture level from three perspectives. Specifically, we develop different structures for speaker and content encoders based on their underlying static/dynamic property. We further propose a generative graph, modelled by S2CD, so as to make S2CD well mimic the multi-speaker speech generation process. Finally, we propose a self-heuristic way to introduce bias …

Fooctts: Generating Arabic Speech With Acoustic Environment For Football Commentator, Massa Baali, Ahmed Ali

Machine Learning Faculty Publications

This paper presents FOOCTTS, an automatic pipeline for a football commentator that generates speech with background crowd noise. The application gets the text from the user, applies text pre-processing such as vowelization, followed by the commentator's speech synthesizer. Our pipeline included Arabic automatic speech recognition for data labeling, CTC segmentation, transcription vowelization to match speech, and fine-tuning the TTS. Our system is capable of generating speech with its acoustic environment within limited 15 minutes of football commentator recording. Our prototype is generalizable and can be easily applied to different domains and languages.

Controllable Language Generation Using Deep Learning, Rohola Zandie

Electronic Theses and Dissertations

The advent of deep neural networks has sparked a revolution in Artificial Intelligence (AI), notably with the creation of Transformer models like GPT-X and ChatGPT. These models have surpassed previous methods in various Natural Language Processing (NLP) tasks. As the NLP field evolves, there is a need to further understand and question the capabilities of these models. Text generation, a crucial part of NLP, remains an area where our comprehension is limited while being critical in research.

This dissertation focuses on the challenging problem of controlling the general behaviors of language models such as sentiment, topical focus, and logical reasoning. …

Terrain And Adversary-Aware Autonomous Robot Navigation, Aniekan Ufot Inyang

Electronic Theses and Dissertations

In autonomous robot navigation, the robot is able to understand the environment around it for intelligent navigation. From its world model of this environment, it generates a global plan for navigation from a position to a goal based on different factors. This research aims to implement autonomous robot navigation by learning terrain affordances: traversability (moving quickly) and concealment (staying hidden from an adversary) using the Preference-based Inverse Reward Learning (PbIRL) methodology. The PbIRL methodology reduces the barrier of generating initial demonstration data to learn the terrain affordances by using a human expert’s preferences to learn individual weights over the terrain …

Topology Optimization For Artificial Neural Networks, Justin Mills

Masters Theses & Specialist Projects

This thesis examines the feasibility of implementing two simple optimization methods, namely the Weights Power method (Hagiwara, 1994) and the Tabu Search method (Gupta & Raza, 2020), within an existing framework. The study centers around the generation of artificial neural networks using these methods, assessing their performance in terms of both accuracy and the capacity to reduce components within the Artificial Neural Network’s (ANN) topology.

The evaluation is conducted on three classification datasets: Air Quality (Shahane, 2021), Diabetes (Soni, 2021), and MNIST (Deng, 2012). The main performance metric used is accuracy, which measures the network's predictive capability for the classification …

Evaluating Chatgpt For Recommendation: How Does The Ability To Converse Impact Recommendation?, Kyle Spurlock

Electronic Theses and Dissertations

Recommendation algorithms have become an absolute necessity in the modern world to avoid information overload. However, the interaction between the human and the system is largely superficial and without any real contact. If you are given poor recommendations, you have no choice but to sift through mountains of content on your own until the model learns to accommodate your tastes more. This is bad for business as well as the consumer. Recently, large language models like ChatGPT have seen a significant rise in popularity due to their ease of use and wide range of knowledge. It has now become nearly …

Application Of Machine Learning Algorithms For Elucidation Of Biological Networks From Time Series Gene Expression Data, Krupa Nagori

Computational and Data Sciences (PhD) Dissertations

This dissertation provides a deep dive into understanding gene expression, interaction, regulation, and the intricate mechanisms behind heliotropism and phototropism. Additionally, the research accentuates the significance of machine learning techniques, specifically for gene regulatory networks (GRNs).

Chapter 1 offers an exhaustive benchmarking of GRN methodologies, furthering our comprehension of machine-learning models relevant to GRNs. The evaluation revealed that GRNTE, SWING, and BiXGBoost emerged as top-performing methods in GRN inference. The suitability of these models varies depending on specific research criteria such as computational needs, dataset dimensions, and performance metric emphasis. An innovation of this chapter was the introduction of Colab …

Seek And Classify: End-To-End Joint Multi-Signal Detection And Classification Using Deep Learning, Prashant Subedi

School of Computing: Dissertations, Theses, and Student Research

The rise in the use of wireless communication has led to the problem of spectrum scarcity in licensed bands. The popularity of Internet of Things (IoT) requires innovative solutions that maximize the use of available spectrum to support the increasing number of connected devices. This thesis tackles two significant problems in wireless communication: the need for efficient spectrum sensing techniques and the scarcity of large, diverse raw in-phase (I) and quadrature (Q) datasets.

The ability to detect and classify modulation of the signals efficiently can enable a cognitive radio to monitor the spectrum activity in real time and utilize unused …

Geospatial Wildfire Risk Prediction Using Deep Learning, Abner Alberto Benavides

Electronic Theses, Projects, and Dissertations

This report introduces a thorough analysis of wildfire prediction using satellite imagery by applying deep learning techniques. To find wildfire-prone geographical data, we use U-Net, a convolutional neural network known for its effectiveness in biomedical image segmentation. The input to the model is the Sentinel-2 multispectral images to supply a complete view of the terrain features.

We evaluated the wildfire risk prediction model’s performance using several metrics. The model showed high accuracy, with a weighted average F1 score of 0.91 and an AUC-ROC score of 0.972. These results suggest that the model is exceptionally good at predicting the location of …

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 …

Towards A Robust Defense: A Multifaceted Approach To The Detection And Mitigation Of Neural Backdoor Attacks Through Feature Space Exploration And Analysis, Liuwan Zhu

Electrical & Computer Engineering Theses & Dissertations

From voice assistants to self-driving vehicles, machine learning(ML), especially deep learning, revolutionizes the way we work and live, through the wide adoption in a broad range of applications. Unfortunately, this widespread use makes deep learning-based systems a desirable target for cyberattacks, such as generating adversarial examples to fool a deep learning system to make wrong decisions. In particular, many recent studies have revealed that attackers can corrupt the training of a deep learning model, e.g., through data poisoning, or distribute a deep learning model they created with “backdoors” planted, e.g., distributed as part of a software library, so that the …

Facial Expression Recognition Using Convolutional Neural Networks (Cnns) And Generative Adversarial Networks (Gans) For Data Augmentation And Image Generation, Shekhar Singh

UNLV Theses, Dissertations, Professional Papers, and Capstones

Facial expressions play a crucial role in human communication, serving as a powerful means to convey emotions. However, classifying facial expressions using artificial intelligence (AI) can be challenging, especially with small datasets and images. Facial Expression Recognition (FER) is an active area of research, with Convolutional Neural Networks (CNNs) being widely employed for classification. In this research, we propose a CNN-based approach for FER that utilizes both original and augmented datasets to enhance classification accuracy. Experimental results on the FER2013 dataset show test accuracies of 63.39% and 64.59% for the original and augmented datasets, respectively, in a seven-class classification task. …

Cannabidiol Tweet Miner: A Framework For Identifying Misinformation In Cbd Tweets., Jason Turner

Electronic Theses and Dissertations

As regulations surrounding cannabis continue to develop, the demand for cannabis-based products is on the rise. Despite not producing the psychoactive effects commonly associated with THC, products containing cannabidiol (CBD) have gained immense popularity in recent years as a potential treatment option for a range of conditions, particularly those associated with pain or sleep disorders. However, due to current federal policies, these products have yet to undergo comprehensive safety and efficacy testing. Fortunately, utilizing advanced natural language processing (NLP) techniques, data harvested from social networks have been employed to investigate various social trends within healthcare, such as disease tracking and …

Inverse Mappers For Qcd Global Analysis, Manal Almaeen

Computer Science Theses & Dissertations

Inverse problems – using measured observations to determine unknown parameters – are well motivated but challenging in many scientific problems. Mapping parameters to observables is a well-posed problem with unique solutions, and therefore can be solved with differential equations or linear algebra solvers. However, the inverse problem requires backward mapping from observable to parameter space, which is often nonunique. Consequently, solving inverse problems is ill-posed and a far more challenging computational problem.

Our motivated application in this dissertation is the inverse problems in nuclear physics that characterize the internal structure of the hadrons. We first present a machine learning framework …

The Development Of Artificial Intelligence-Based To Ols For Expert Peer Review Of Radiotherapy Treatment Plans, Mary Gronberg

Dissertations and Theses (Open Access)

Creating a patient-specific radiation treatment plan is a time-consuming and operator-dependent manual process. The treatment planner adjusts the planning parameters in a trial-and-error fashion in an effort to balance the competing clinical objectives of tumor coverage and normal tissue sparing. Often, a plan is selected because it meets basic organ at risk dose thresholds for severe toxicity; however, it is evident that a plan with a decreased risk of normal tissue complication probability could be achieved. This discrepancy between “acceptable” and “best possible” plan is magnified if either the physician or treatment planner lacks focal expertise in the disease site. …

Epileptic Seizure Classification Using Image-Based Data Representation, Amber Surles

Graduate Theses and Dissertations (2019 - present)

Epilepsy is a recurrence of seizures caused by a disorder of the brain in over 3.4 million people nationwide. Some people are able to predict their seizures based off prodrome, which is an early sign or symptom that usually resembles mood changes or a euphoric feeling even days to an hour before occurrence. Consequently, the natural instincts of the body to react to an upcoming attack lends credence to the existence of a pre-ictal state that precedes seizure episodes. Physicians and researchers have thus sought for an automated approach for predicting or detecting seizures.

In this research, we evaluate the …

Data Is The New Gold: A Singapore Perspective On The Duty Of Care Concerning A Dataset’S Role In Contributing To Bias And Ai Hallucinations, Daniel Seah

Research Collection College of Integrative Studies

Amidst the trends and advances in Artificial Intelligence (AI) techniques, the dataset’s key role in creating AI harms is a constant. Yet the literature’s attention is typically focussed on the machinelearning’s role, from which the dataset’s role is examined usually in terms of its potential for bias. Datasets also contribute to AI hallucinations. Again, the literature focuses on the composite roles of datasets and AI models in hallucinations, in isolation from a dataset’s contributory role in creating bias. Therefore, the overlapping and distinctive roles of datasets, as a dual contributor, are understudied in the literature. Through the legal concept of …

Generalization Through Diversity: Improving Unsupervised Environment Design, Wenjun Li, Pradeep Varakantham, Dexun Li

Research Collection School Of Computing and Information Systems

Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board). Due to this dependence, small changes in the environment (e.g., positions of obstacles in the maze, size of the board) can severely affect the effectiveness of the policy learned by the agent. To that end, existing work has proposed training RL agents on an adaptive curriculum of environments (generated automatically) to improve performance on out-of-distribution (OOD) test scenarios. Specifically, existing research has employed the potential for the …

Numgpt: Improving Numeracy Ability Of Generative Pre-Trained Models, Zhihua Jin, Xin Jiang, Xiangbo Wang, Qun Liu, Yong Wang, Xiaozhe Ren, Huamin Qu

Research Collection School Of Computing and Information Systems

Existing generative pre-trained language models (e.g., GPT) focus on modeling the language structure and semantics of general texts. However, those models do not consider the numerical properties of numbers and cannot perform robustly on numerical reasoning tasks (e.g., math word problems and measurement estimation). In this paper, we propose NumGPT, a generative pre-trained model that explicitly models the numerical properties of numbers in texts. Specifically, it leverages a prototype-based numeral embedding to encode the mantissa of the number and an individual embedding to encode the exponent of the number. A numeral-aware loss function is designed to integrate numerals into the …

Towards Intelligent Runtime Framework For Distributed Heterogeneous Systems, Polykarpos Thomadakis

Computer Science Theses & Dissertations

Scientific applications strive for increased memory and computing performance, requiring massive amounts of data and time to produce results. Applications utilize large-scale, parallel computing platforms with advanced architectures to accommodate their needs. However, developing performance-portable applications for modern, heterogeneous platforms requires lots of effort and expertise in both the application and systems domains. This is more relevant for unstructured applications whose workflow is not statically predictable due to their heavily data-dependent nature. One possible solution for this problem is the introduction of an intelligent Domain-Specific Language (iDSL) that transparently helps to maintain correctness, hides the idiosyncrasies of lowlevel hardware, and …