Artificial Intelligence and Robotics Commons^™

A Machine Learning Framework To Classify Mosquito Species From Smart-Phone Images, Mona Minakshi

USF Tampa Graduate Theses and Dissertations

Mosquito borne diseases have been a constant scourge across the globe resulting in numerous diseases with debilitating consequences, and also death. To derive trends on population of mosquitoes in an area, trained personnel lay traps, and after collecting trapped specimens, they spend hours under a microscope to inspect each specimen for identifying the actual species and logging it. This is vital, because multiple species of mosquitoes can reside in any area, and the vectors that some of them carry are not the same ones carried by others. The species identification process is naturally laborious, and imposes severe cognitive burden, since …

Deep Learning For Link Prediction In Dynamic Networks Using Weak Estimators, Carter Chiu, Justin Zhan

Computer Science Faculty Research

Link prediction is the task of evaluating the probability that an edge exists in a network, and it has useful applications in many domains. Traditional approaches rely on measuring the similarity between two nodes in a static context. Recent research has focused on extending link prediction to a dynamic setting, predicting the creation and destruction of links in networks that evolve over time. Though a difficult task, the employment of deep learning techniques have shown to make notable improvements to the accuracy of predictions. To this end, we propose the novel application of weak estimators in addition to the utilization …

Augustana Invitational Robotics Challenge 2018, Forrest Stonedahl

Celebration of Learning

We will be hosting the 3rd Annual Augustana Invitational Robotics Challenge. This event will involve student teams from Augustana and potentially several other schools in the region bringing forth the robots that they have designed, built, and programmed, to compete against one another. This year's challenge task involves the careful relocation of soda pop cans.

Cuoricino Thermal Pulse Classification By Machine Learning Algorithms, Joshua Mann

Physics

Many of the various properties of neutrinos are still a mystery. One unknown is whether neutrinos are Majorana fermions or Dirac fermions. Cuoricino and CUORE are experiments that aim to solve this mystery. Noise reduction in these experiments hinges on the ability to discern among alpha, beta and gamma particle detections using the thermal pulses they create. In this paper, we look at Cuoricino data and attempt to classify pulses, not as alpha, beta or gamma particles, but rather as signal, noise or calibration data. We will use this preliminary testing ground to examine various machine learning algorithms' abilities in …

Extractive Text Summarization With Deep Learning, Garrett G. Chan

Computer Engineering

This project explores extractive text summarization using the capabilities of Deep Learning. The goal of this project is to create an application with a neural network to take in text as its input, and create a summary that is a shorter, condensed version of the input text. This has been implemented in Python by configuring and training a neural network that takes in a vector of features that are extracted from the text using various Natural Language Processing libraries. The implementation demonstrates that we can train simple deep neural networks to successfully summarize text.

The Effect Of Endgame Tablebases On Modern Chess Engines, Christopher D. Peterson

Computer Engineering

Modern chess engines have the ability to augment their evaluation by using massive tables containing billions of positions and their memorized solutions. This report examines the importance of these tables to better understand the circumstances under which they should be used. The analysis conducted in this paper empirically examines differences in size and speed of memorized positions and their impacts on engine strength. Using this technique, situations where memorized tables improve play (and situations where they do not) are discovered.

Influencing Exploration In Actor-Critic Reinforcement Learning Algorithms, Andrew R. Gough

Master's Theses

Reinforcement Learning (RL) is a subset of machine learning primarily concerned with goal-directed learning and optimal decision making. RL agents learn based on a reward signal discovered from trial and error in complex, uncertain environments with the goal of maximizing positive reward signals. RL approaches need to scale up as they are applied to more complex environments with extremely large state spaces. Inefficient exploration methods cannot sufficiently explore complex environments in a reasonable amount of time, and optimal policies will be unrealized resulting in RL agents failing to solve an environment.

This thesis proposes a novel variant of the Actor-Advantage …

Reserved Optimisation: Handling Incident Priorities In Emergency Response Systems, Muralidhar Konda, Supriyo Ghosh, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Emergency (medical, fire or criminal) Management Systems(EMSs) are crucial for ensuring public safety and security. Typically in many cities, less than 20% of the cases received by EMSs belong to the extremely serious category and require immediate help. Rest of the incidents typically are less serious and thereby allow more flexibility in response time. Therefore, for efficient management of EMS requests, several EMSs now categorise an incoming emergency request into apriority level based on well studied “triaging” methods. Leading research on optimising emergency response has either focussed on data-driven models for settings with homogenous incidents or on generic heuristics (that …

Instance-Specific Selection Of Aos Methods For Solving Combinatorial Optimisation Problems Via Neural Networks, Teck Hou (Deng Dehao) Teng, Hoong Chuin Lau, Aldy Gunawan

Research Collection School Of Computing and Information Systems

Solving combinatorial optimization problems using a fixed set of operators has been known to produce poor quality solutions. Thus, adaptive operator selection (AOS) methods have been proposed. But, despite such effort, challenges such as the choice of suitable AOS method and configuring it correctly for given specific problem instances remain. To overcome these challenges, this work proposes a novel approach known as I-AOS-DOE to perform Instance-specific selection of AOS methods prior to evolutionary search. Furthermore, to configure the AOS methods for the respective problem instances, we apply a Design of Experiment (DOE) technique to determine promising regions of parameter values …

Analysing Multi-Point Multi-Frequency Machine Vibrations Using Optical Sampling, Dibyendu Roy, Avik Ghose, Tapas Chakravarty, Sushovan Mukherjee, Arpan Pal, Archan Misra

Research Collection School Of Computing and Information Systems

Vibration analysis is a key troubleshooting methodology for assessing the health of factory machinery. We propose an unobtrusive framework for at-a-distance visual estimation of such (possibly high frequency) vibrations, using a low fps (frames-per-second) camera that may, for example, be mounted on a worker's smart-glass. Our key innovation is to use an external stroboscopic light source (that, for example, may be provided by an assistive robot), to illuminate the machine with multiple mutually-prime strobing frequencies, and use the resulting aliased signals to efficiently estimate the different vibration frequencies via an enhanced version of the Chinese Remainder Theorem. Experimental results show …

Disentangled Person Image Generation, Liqian Ma, Qianru Sun, Stamatios Georgoulis, Luc Van Gool, Bernt Schiele, Mario Fritz

Research Collection School Of Computing and Information Systems

Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such images based on a novel, two-stage reconstruction pipeline that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time. First, a multi-branched reconstruction network is proposed to disentangle and encode the three factors into embedding features, which are then combined to re-compose the input image itself. Second, three corresponding mapping functions are learned in an …

Natural And Effective Obfuscation By Head Inpainting, Qianru Sun, Liqian Ma, Seong Joon Oh, Luc Van Gool, Bernt Schiele, Mario Fritz

Research Collection School Of Computing and Information Systems

As more and more personal photos are shared online, being able to obfuscate identities in such photos is becoming a necessity for privacy protection. People have largely resorted to blacking out or blurring head regions, but they result in poor user experience while being surprisingly ineffective against state of the art person recognizers. In this work, we propose a novel head inpainting obfuscation technique. Generating a realistic head inpainting in social media photos is challenging because subjects appear in diverse activities and head orientations. We thus split the task into two sub-tasks: (1) facial landmark generation from image context (e.g. …

An Investigation Into The Effects Of Multiple Kernel Combinations On Solutions Spaces In Support Vector Machines, Paul Kelly, Luca Longo

Conference papers

The use of Multiple Kernel Learning (MKL) for Support Vector Machines (SVM) in Machine Learning tasks is a growing field of study. MKL kernels expand on traditional base kernels that are used to improve performance on non-linearly separable datasets. Multiple kernels use combinations of those base kernels to develop novel kernel shapes that allow for more diversity in the generated solution spaces. Customising these kernels to the dataset is still mostly a process of trial and error. Guidelines around what combinations to implement are lacking and usually they requires domain specific knowledge and understanding of the data. Through a brute …

Detecting Rip Currents From Images, Corey C. Maryan

LSU New Orleans Theses and Dissertations

Rip current images are useful for assisting in climate studies but time consuming to manually annotate by hand over thousands of images. Object detection is a possible solution for automatic annotation because of its success and popularity in identifying regions of interest in images, such as human faces. Similarly to faces, rip currents have distinct features that set them apart from other areas of an image, such as more generic patterns of the surf zone. There are many distinct methods of object detection applied in face detection research. In this thesis, the best fit for a rip current object detector …

Detecting Metagame Shifts In League Of Legends Using Unsupervised Learning, Dustin P. Peabody

LSU New Orleans Theses and Dissertations

Over the many years since their inception, the complexity of video games has risen considerably. With this increase in complexity comes an increase in the number of possible choices for players and increased difficultly for developers who try to balance the effectiveness of these choices. In this thesis we demonstrate that unsupervised learning can give game developers extra insight into their own games, providing them with a tool that can potentially alert them to problems faster than they would otherwise be able to find. Specifically, we use DBSCAN to look at League of Legends and the metagame players have formed …

Applications Of Artificial Intelligence In Power Systems, Samin Rastgoufard

LSU New Orleans Theses and Dissertations

Artificial intelligence tools, which are fast, robust and adaptive can overcome the drawbacks of traditional solutions for several power systems problems. In this work, applications of AI techniques have been studied for solving two important problems in power systems.

The first problem is static security evaluation (SSE). The objective of SSE is to identify the contingencies in planning and operations of power systems. Numerical conventional solutions are time-consuming, computationally expensive, and are not suitable for online applications. SSE may be considered as a binary-classification, multi-classification or regression problem. In this work, multi-support vector machine is combined with several evolutionary computation …

Automatic Conversation Review For Intelligent Virtual Assistants, Ian R. Beaver

Computer Science ETDs

When reviewing the performance of Intelligent Virtual Assistants (IVAs), it is desirable to prioritize conversations involving misunderstood human inputs. These conversations uncover error in natural language understanding and help prioritize and expedite improvements to the IVA. As human reviewer time is valuable and manual analysis is time consuming, prioritizing the conversations where misunderstanding has likely occurred reduces costs and speeds improvement. A system for measuring the posthoc risk of missed intent associated with a single human input is presented. Numerous indicators of risk are explored and implemented. These indicators are combined using various means and evaluated on real world data. …

Ai-Human Collaboration Via Eeg, Adam Noack

All College Thesis Program, 2016-2019

As AI becomes ever more competent and integrated into our lives, the issue of AI-human goal misalignment looms larger. This is partially because there is often a rift between what humans explicitly command and what they actually mean. Most contemporary AI systems cannot bridge this gap. In this study we attempted to reconcile the goals of human and machine by using EEG signals from a human to help a simulated agent complete a task.

Computer Vision Evidence Supporting Craniometric Alignment Of Rat Brain Atlases To Streamline Expert-Guided, First-Order Migration Of Hypothalamic Spatial Datasets Related To Behavioral Control, Arshad Khan, Jose Perez, Claire Wells, Olac Fuentes

Selected Works Temporary Series

The rat has arguably the most widely studied brain among all animals, with numerous reference atlases for rat brain having been published since 1946. For example, many neuroscientists have used the atlases of Paxinos and Watson (PW, first published in 1982) or Swanson (S, first published in 1992) as guides to probe or map specific rat brain structures and their connections. Despite nearly three decades of contemporaneous publication, no independent attempt has been made to establish a basic framework that allows data mapped in PW to be placed in register with S, or vice versa. Such data migration would allow …

Self-Organized Structures: Modeling Polistes Dominula Nest Construction With Simple Rules, Matthew Harrison

Electronic Theses and Dissertations

The self-organized nest construction behaviors of European paper wasps (Polistes dominula) show potential for adoption in artificial intelligence and robotic systems where centralized control proves challenging. However, P. dominula nest construction mechanisms are not fully understood. This research investigated how nest structures stimulate P. dominula worker action at different stages of nest construction. A novel stochastic site selection model, weighted by simple rules for cell age, height, and wall count, was implemented in a three-dimensional, step-by-step nest construction simulation. The simulation was built on top of a hexagonal coordinate system to improve precision and performance. Real and idealized …

Computer Vision Evidence Supporting Craniometric Alignment Of Rat Brain Atlases To Streamline Expert-Guided, First-Order Migration Of Hypothalamic Spatial Datasets Related To Behavioral Control, Khan, Jose Perez, Claire Wells, Olac Fuentes

Departmental Papers (Biology)

The rat has arguably the most widely studied brain among all animals, with numerous reference atlases for rat brain having been published since 1946. For example, many neuroscientists have used the atlases of Paxinos and Watson (PW, first published in 1982) or Swanson (S, first published in 1992) as guides to probe or map specific rat brain structures and their connections. Despite nearly three decades of contemporaneous publication, no independent attempt has been made to establish a basic framework that allows data mapped in PW to be placed in register with S, or vice versa. …

Evaluating Sequence Discovery Systems In An Abstraction-Aware Manner, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

Activity discovery is a challenging machine learning problem where we seek to uncover new or altered behavioural patterns in sensor data. In this paper we motivate and introduce a novel approach to evaluating activity discovery systems. Pre-annotated ground truths, often used to evaluate the performance of such systems on existing datasets, may exist at different levels of abstraction to the output of the output produced by the system. We propose a method for detecting and dealing with this situation, allowing for useful ground truth comparisons. This work has applications for activity discovery, and also for related fields. For example, it …

Ai: Augmentation, More So Than Automation, Steven M. Miller

Asian Management Insights

The take-up of Artificial Intelligence (AI)-enabled systems in organisations is expanding rapidly. Integrating AI-enabled automation with people into workplace processes and societal systems is a complex and evolving challenge. The articles takes a managerial perspective on how firms can effectively deploy human minds and intelligent machines in the workplace.

Self-Reconfiguration Planning In Modular Reconfigurable Robots, Keaton Griffith

Honors Theses

MSRs are highly versatile robots that work together to form into different configurations. However, to take advantage of this ability to transform, the MSR must utilize an SRP algorithm to determine what actions to perform to shape itself to reach its goal configuration. An SRP algorithm can be boiled down to a search method through an unexplored graph which we approach with four basic search algorithms to see which algorithm is best when designing an SRP algorithm. To do this we create a general MSR model known as stickbots and use different search algorithms on a variety of SRP problems …

Effectively Enforcing Minimality During Backtrack Search, Daniel J. Geschwender

School of Computing: Dissertations, Theses, and Student Research

Constraint Processing is an expressive and powerful framework for modeling and solving combinatorial decision problems. Enforcing consistency during backtrack search is an effective technique for reducing thrashing in a large search tree. The higher the level of the consistency enforced, the stronger the pruning of inconsistent subtrees. Recently, high-level consistencies (HLC) were shown to be instrumental for solving difficult instances. In particular, minimality, which is guaranteed to prune all inconsistent branches, is advantageous even when enforced locally. In this thesis, we study two algorithms for computing minimality and propose three new mechanisms that significantly improve performance. Then, we integrate the …

Parameterizing And Aggregating Activation Functions In Deep Neural Networks, Luke Benjamin Godfrey

Graduate Theses and Dissertations

The nonlinear activation functions applied by each neuron in a neural network are essential for making neural networks powerful representational models. If these are omitted, even deep neural networks reduce to simple linear regression due to the fact that a linear combination of linear combinations is still a linear combination. In much of the existing literature on neural networks, just one or two activation functions are selected for the entire network, even though the use of heterogenous activation functions has been shown to produce superior results in some cases. Even less often employed are activation functions that can adapt their …

Adaptation And Augmentation: Towards Better Rescoring Strategies For Automatic Speech Recognition And Spoken Term Detection, Min Ma

Dissertations, Theses, and Capstone Projects

Selecting the best prediction from a set of candidates is an essential problem for many spoken language processing tasks, including automatic speech recognition (ASR) and spoken keyword spotting (KWS). Generally, the selection is determined by a confidence score assigned to each candidate. Calibrating these confidence scores (i.e., rescoring them) could make better selections and improve the system performance. This dissertation focuses on using tailored language models to rescore ASR hypotheses as well as keyword search results for ASR-based KWS.

This dissertation introduces three kinds of rescoring techniques: (1) Freezing most model parameters while fine-tuning the output layer in order to …

Multimodal Depression Detection: An Investigation Of Features And Fusion Techniques For Automated Systems, Michelle Renee Morales

Dissertations, Theses, and Capstone Projects

Depression is a serious illness that affects a large portion of the world’s population. Given the large effect it has on society, it is evident that depression is a serious health issue. This thesis evaluates, at length, how technology may aid in assessing depression. We present an in-depth investigation of features and fusion techniques for depression detection systems. We also present OpenMM: a novel tool for multimodal feature extraction. Lastly, we present novel techniques for multimodal fusion. The contributions of this work add considerably to our knowledge of depression detection systems and have the potential to improve future systems by …

Multi Self-Adapting Particle Swarm Optimization Algorithm (Msapso)., Gerhard Koch

Electronic Theses and Dissertations

The performance and stability of the Particle Swarm Optimization algorithm depends on parameters that are typically tuned manually or adapted based on knowledge from empirical parameter studies. Such parameter selection is ineffectual when faced with a broad range of problem types, which often hinders the adoption of PSO to real world problems. This dissertation develops a dynamic self-optimization approach for the respective parameters (inertia weight, social and cognition). The effects of self-adaption for the optimal balance between superior performance (convergence) and the robustness (divergence) of the algorithm with regard to both simple and complex benchmark functions is investigated. This work …

Al Planning Assistant For Scheduling Daily Activities, Priyanka Ahuja

Theses and Dissertations

Artificial conversational agents are software agents that can interact with humans in the way humans do. Siri Cortana, and Alexa are examples of intelligent agents that can help us with almost all the basic tasks. These agents are smart enough to do the basic tasks, but not as much when it comes to complex tasks, such as analyzing traffic data, reviewing scheduling conflicts, rescheduling meetings while resolving conflicts, and offering suggestions based upon data analyses (e.g. traffic patterns, weather, etc.) The actual potential of dialogue-based task agent potential remains untapped. The reason is the fact agents lack the ability to …