Artificial Intelligence and Robotics Commons^™

Multi-Modal Classification Using Images And Text, Stuart J. Miller, Justin Howard, Paul Adams, Mel Schwan, Robert Slater

SMU Data Science Review

This paper proposes a method for the integration of natural language understanding in image classification to improve classification accuracy by making use of associated metadata. Traditionally, only image features have been used in the classification process; however, metadata accompanies images from many sources. This study implemented a multi-modal image classification model that combines convolutional methods with natural language understanding of descriptions, titles, and tags to improve image classification. The novelty of this approach was to learn from additional external features associated with the images using natural language understanding with transfer learning. It was found that the combination of ResNet-50 image …

Low Light Image Enhancement Via Global And Local Context Modeling, Aditya Arora, Muhammad Haris, Syed Waqas Zamir, Munawar Hayat, Fahad Shahbaz Khan, Ling Shao, Ming-Hsuan Yang

Computer Vision Faculty Publications

Images captured under low-light conditions manifest poor visibility, lack contrast and color vividness. Compared to conventional approaches, deep convolutional neural networks (CNNs) perform well in enhancing images. However, being solely reliant on confined fixed primitives to model dependencies, existing data-driven deep models do not exploit the contexts at various spatial scales to address low-light image enhancement. These contexts can be crucial towards inferring several image enhancement tasks, e.g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent. To this end, we introduce a context-aware deep network for low-light image enhancement. First, …

Using Torchattacks To Improve The Robustness Of Models With Adversarial Training, William S. Matos Díaz

Cybersecurity: Deep Learning Driven Cybersecurity Research in a Multidisciplinary Environment

Adversarial training has proven to be one of the most successful ways to defend models against adversarial examples. This process consists of training a model with an adversarial example to improve the robustness of the model. In this experiment, Torchattacks, a Pytorch library made for importing adversarial examples more easily, was used to determine which attack was the strongest. Later on, the strongest attack was used to train the model and make it more robust against adversarial examples. The datasets used to perform the experiments were MNIST and CIFAR-10. Both datasets were put to the test using PGD, FGSM, and …

Fireeye: Cybersecurity In Action, Singapore Management University

Perspectives@SMU

FireEye built its success on its ‘Human + AI’ philosophy. But can a cybersecurity firm get ahead of the attackers and predict an attack…on itself?

Fairer Evaluation Of Zero Shot Action Recognition In Videos, Kaiqiang Huang, Sarah Jane Delany, Susan Mckeever

Conference Papers

Zero-shot learning (ZSL) for human action recognition (HAR) aims to recognise video action classes that have never been seen during model training. This is achieved by building mappings between visual and semantic embeddings. These visual embeddings are typically provided via a pre-trained deep neural network (DNN). The premise of ZSL is that the training and testing classes should be disjoint. In the parallel domain of ZSL for image input, the widespread poor evaluation protocol of pre-training on ZSL test classes has been highlighted. This is akin to providing a sneak preview of the evaluation classes. In this work, we investigate …

Wind Turbine Parameter Calibration Using Deep Learning Approaches, Rebecca Mccubbin

Electronic Theses and Dissertations

The inertia and damping coefficients are critical to understanding the workings of a wind turbine, especially when it is in a transient state. However, many manufacturers do not provide this information about their turbines, requiring people to estimate these values themselves. This research seeks to design a multilayer perceptron (MLP) that can accurately predict the inertia and damping coefficients using the power data from a turbine during a transient state. To do this, a model of a wind turbine was built in Matlab, and a simulation of a three-phase fault was used to collect realistic fault data to input into …

Deep Learning For High-Impedance Fault Detection: Convolutional Autoencoders, Khushwant Rai, Firouz Badrkhani Ajaei, Farnam Hojatpanah, Katarina Grolinger

Electrical and Computer Engineering Publications

High-impedance faults (HIF) are difficult to detect because of their low current amplitude and highly diverse characteristics. In recent years, machine learning (ML) has been gaining popularity in HIF detection because ML techniques learn patterns from data and successfully detect HIFs. However, as these methods are based on supervised learning, they fail to reliably detect any scenario, fault or non-fault, not present in the training data. Consequently, this paper takes advantage of unsupervised learning and proposes a convolutional autoencoder framework for HIF detection (CAE-HIFD). Contrary to the conventional autoencoders that learn from normal behavior, the convolutional autoencoder (CAE) in CAE-HIFD …

Simplification Of Robotics Through Autonomous Navigation, Grant Turner

Mahurin Honors College Capstone Experience/Thesis Projects

With self-driving vehicles, college campus food delivery, or even automated home vacuuming systems, robotics is undoubtedly becoming more prevalent in everyday society and it can be expected to continue with time. While many people are owners, users, or even just spectators of theses robotic products or services, there seems to be a negative perception of robotics that poses an intimidation factor regarding the attempt to understand the ideas driving technology. This perception tends to view robotics as machines that require rich education to understand the complexity and interworkings of, thus attempts understand the field are neglected.

To combat this line …

Unsupervised Meta-Learning, Siavash Khodadadeh

Electronic Theses and Dissertations, 2020-2023

Deep learning has achieved classification performance matching or exceeding the human one, as long as plentiful labeled training samples are available. However, the performance on few-shot learning, where the classifier had seen only several or possibly only one sample of the class is still significantly below human performance. Recently, a type of algorithm called meta-learning achieved impressive performance for few-shot learning. However, meta-learning requires a large dataset of labeled tasks closely related to the test task. The work described in this dissertation outlines techniques that significantly reduce the need for expensive and scarce labeled data in the meta-learning phase. Our …

Tackling Ai Bias With Gans, Noam Stanislawski

Cybersecurity Undergraduate Research Showcase

Throughout the relatively short history of artificial intelligence (AI), there has been a significant concern surrounding AI’s ability to incorporate and maintain certain characteristics which were not inherently modeled out in its coding. These behaviors stem from the prominent usage of neural network AI, which can inherit human biases from the input data it receives. This paper argues for two possible avenues to combat these biases. The first is to rethink the traditional framework for neural network projects and retool them to be usable by a Generative Adversarial Network (GAN). In a GAN’s zero-sum game, two network techniques can combat …

Visual Learning Beyond Human Curated Datasets, Muhammad Abdullah Jamal

Electronic Theses and Dissertations, 2020-2023

The success of deep neural networks in a variety of computer vision tasks heavily relies on large- scale datasets. However, it is expensive to manually acquire labels for large datasets. Given the human annotation cost and scarcity of data, the challenge is to learn efficiently with insufficiently labeled data. In this dissertation, we propose several approaches towards data-efficient learning in the context of few-shot learning, long-tailed visual recognition, and unsupervised and semi-supervised learning. In the first part, we propose a novel paradigm of Task-Agnostic Meta- Learning (TAML) algorithms to improve few-shot learning. Furthermore, in the second part, we analyze the …

Playing Pong Using Q-Learning, Akash Kumar

West Chester University Master’s Theses

This thesis involves the use of a reinforcement learning algorithm (RL) called Q-learning to train a Q-agent to play a game of Pong against a near-perfect opponent. Compared to previously related work which trained Pong RL agents by combining Q-learning with deep learning in an algorithm known as Deep Q-Networks, the work presented in this paper takes advantage of known environment constraints of the custom-made Pong environment to train the agent using one-step Q-learning alone. In addition, the thesis explores ways of making the Q-learning more efficient by converting Markov Decision Processes (MDPs) to Partially Observable Markov Decision Processes (POMDPs), …

Computational Intelligent Impact Force Modeling And Monitoring In Hislo Conditions For Maximizing Surface Mining Efficiency, Safety, And Health, Danish Ali

Doctoral Dissertations

"Shovel-truck systems are the most widely employed excavation and material handling systems for surface mining operations. During this process, a high-impact shovel loading operation (HISLO) produces large forces that cause extreme whole body vibrations (WBV) that can severely affect the safety and health of haul truck operators. Previously developed solutions have failed to produce satisfactory results as the vibrations at the truck operator seat still exceed the “Extremely Uncomfortable Limits”. This study was a novel effort in developing deep learning-based solution to the HISLO problem.

This research study developed a rigorous mathematical model and a 3D virtual simulation model to …

Reliable And Interpretable Machine Learning For Modeling Physical And Cyber Systems, Daniel L. Marino Lizarazo

Theses and Dissertations

Over the past decade, Machine Learning (ML) research has predominantly focused on building extremely complex models in order to improve predictive performance. The idea was that performance can be improved by adding complexity to the models. This approach proved to be successful in creating models that can approximate highly complex relationships while taking advantage of large datasets. However, this approach led to extremely complex black-box models that lack reliability and are difficult to interpret. By lack of reliability, we specifically refer to the lack of consistent (unpredictable) behavior in situations outside the training data. Lack of interpretability refers to the …

Maidrl: Semi-Centralized Multi-Agent Reinforcement Learning Using Agent Influence, Anthony Lee Harris

Graduate Theses/Dissertations

In recent years, reinforcement learning algorithms, a subset of machine learning that focuses on solving problems through trial-and-error learning, have been used in the field of multi-agent systems to help the agents with interactions and cooperation on a variety of tasks. Given the enormous success of reinforcement learning in single-agent systems like Chess, Shogi, and Go, it is natural for the next step to be the expansion into multi-agent systems. However, controlling multiple agents simultaneously is extremely challenging, as the complexity increases tremendously with the number of agents in the system. Existing approaches in this regard use a wide range …

Improving Stock Trading Decisions Based On Pattern Recognition Using Machine Learning Technology, Yaohu Lin, Shancun Liu, Haijun Yang, Harris Wu, Bingbing Jiang

Information Technology & Decision Sciences Faculty Publications

PRML, a novel candlestick pattern recognition model using machine learning methods, is proposed to improve stock trading decisions. Four popular machine learning methods and 11 different features types are applied to all possible combinations of daily patterns to start the pattern recognition schedule. Different time windows from one to ten days are used to detect the prediction effect at different periods. An investment strategy is constructed according to the identified candlestick patterns and suitable time window. We deploy PRML for the forecast of all Chinese market stocks from Jan 1, 2000 until Oct 30, 2020. Among them, the data from …

The Role Of Ammonia In Atmospheric New Particle Formation And Implications For Cloud Condensation Nuclei, Arshad Arjunan Nair

Legacy Theses & Dissertations (2009 - 2024)

Atmospheric ammonia has received recent attention due to (a) its increasing trend across various regions of the globe; (b) the associated direct and indirect (through PM2.5) effects on human health, the ecosystem, and climate; and (c) recent evidence of its role in significantly enhancing atmospheric new particle formation (NPF or nucleation) rates. The mechanisms behind nucleation in the atmosphere are not fully understood, although over the last decade there have been significant developments in our understanding. This dissertation aims at improving our understanding of atmospheric ammonia in the atmosphere, its spatiotemporal variability, its role in atmospheric new particle formation, and …

Learning Graphs For Object Tracking And Counting, Shengkun Li

Legacy Theses & Dissertations (2009 - 2024)

As important problems in computer vision, object tracking and counting attract increasing amounts of attention in recent years due to its wide range of applications, such as video surveillance, human- computer interaction, smart city. Despite much progress has been made in object tracking and counting with the arriving of deep neural networks (DNN), there still remains much room for improvement to satisfy the real-world applications.

Interpretable, Not Black-Box, Artificial Intelligence Should Be Used For Embryo Selection, Michael Anis Mihdi Afnan, Yanhe Liu, Vincent Conitzer, Cynthia Rudin, Abhishek Mishra, Julian Savulescu, Masoud Afnan

Research outputs 2014 to 2021

Artificial intelligence (AI) techniques are starting to be used in IVF, in particular for selecting which embryos to transfer to the woman. AI has the potential to process complex data sets, to be better at identifying subtle but important patterns, and to be more objective than humans when evaluating embryos. However, a current review of the literature shows much work is still needed before AI can be ethically implemented for this purpose. No randomized controlled trials (RCTs) have been published, and the efficacy studies which exist demonstrate that algorithms can broadly differentiate well between ‘good-’ and ‘poor-’ quality embryos but …

Large Scale Subject Category Classification Of Scholarly Papers With Deep Attentive Neural Networks, Bharath Kandimalla, Shaurya Rohatgi, Jian Wu, C. Lee Giles

Computer Science Faculty Publications

Subject categories of scholarly papers generally refer to the knowledge domain(s) to which the papers belong, examples being computer science or physics. Subject category classification is a prerequisite for bibliometric studies, organizing scientific publications for domain knowledge extraction, and facilitating faceted searches for digital library search engines. Unfortunately, many academic papers do not have such information as part of their metadata. Most existing methods for solving this task focus on unsupervised learning that often relies on citation networks. However, a complete list of papers citing the current paper may not be readily available. In particular, new papers that have few …