Physical Sciences and Mathematics Commons^™

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 …

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 …

Real-Time Object Recognition Using A Multi-Framed Temporal Approach, Corinne Alini

Honors Projects

Computer Vision involves the extraction of data from images that are analyzed in order to provide information crucial to many modern technologies. Object recognition has proven to be a difficult task and programming reliable object recognition remains elusive. Image processing is computationally intensive and this issue is amplified on mobile platforms with processor restrictions. The real-time constraints demanded by robotic soccer in RoboCup competition serve as an ideal format to test programming that seeks to overcome these challenges. This paper presents a method for ball recognition by analyzing the movement of the ball. Major findings include enhanced ball discrimination by …

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 …

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 …

Effectively Enforcing Minimality During Backtrack Search, Daniel J. Geschwender

Department of Computer Science and Engineering: 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 …

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 …

Design And Implementation Of A Domain Specific Language For Deep Learning, Xiao Bing Huang

Theses and Dissertations

\textit {Deep Learning} (DL) has found great success in well-diversified areas such as machine vision, speech recognition, big data analysis, and multimedia understanding recently. However, the existing state-of-the-art DL frameworks, e.g. Caffe2, Theano, TensorFlow, MxNet, Torch7, and CNTK, are programming libraries with fixed user interfaces, internal representations, and execution environments. Modifying the code of DL layers or data structure is very challenging without in-depth understanding of the underlying implementation. The optimization of the code and execution in these tools is often limited and relies on the specific DL computation graph manipulation and scheduling that lack systematic and universal strategies. Furthermore, …

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 …

Peer Attention Modeling With Head Pose Trajectory Tracking Using Temporal Thermal Maps, Corey Michael Johnson

Masters Theses

Human head pose trajectories can represent a wealth of implicit information such as areas of attention, body language, potential future actions, and more. This signal is of high value for use in Human-Robot teams due to the implicit information encoded within it. Although team-based tasks require both explicit and implicit communication among peers, large team sizes, noisy environments, distance, and mission urgency can inhibit the frequency and quality of explicit communication. The goal for this thesis is to improve the capabilities of Human-Robot teams by making use of implicit communication. In support of this goal, the following hypotheses are investigated: …

File Fragment Classification Using Neural Networks With Lossless Representations, Luke Hiester

Undergraduate Honors Theses

This study explores the use of neural networks as universal models for classifying file fragments. This approach differs from previous work in its lossless feature representation, with fragments’ bits as direct input, and its use of feedforward, recurrent, and convolutional networks as classifiers, whereas previous work has only tested feedforward networks. Due to the study’s exploratory nature, the models were not directly evaluated in a practical setting; rather, easily reproducible experiments were performed to attempt to answer the initial question of whether this approach is worthwhile to pursue further, especially due to its high computational cost. The experiments tested classification …

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 M. Khan, Jose G. Perez, Claire E. Wells, Olac Fuentes

Arshad M. Khan, Ph.D.

Forecasting Smart Meter Energy Usage Using Distributed Systems And Machine Learning, Feiran Ji, Chris Dong, Lingzhi Du, Zizhen Song, Yuedi Zheng, Paul Intrevado

Creative Activity and Research Day - CARD

In this research, we explore the technical and computational merits of a machine learning algorithm on a large data set, employing distributed systems. Using 167 million(10 GB) energy consumption observations collected by smart meters from residential consumers in London, England, we predict future residential energy consumption using a Random Forest machine learning algorithm. Distributed systems such as AWS S3 and EMR, MongoDB and Apache Spark are used. Computational times and predictive accuracy are evaluated. We conclude that there are significant computational advantages to using distributed systems when applying machine learning algorithms on large-scale data. We also observe that distributed systems …

Cerebral Necrosis Research With Machine Learning Techniques, Sangyu Shen

Creative Activity and Research Day - CARD

Cerebral necrosis after radiotherapy for patients with brain metastases is being recognized as a problem more common than previously estimated. To better understand the onset of necrosis and reduce its occurrence, we studied the relationships between features of patients and necrosis onset with machine learning techniques.

An Optimization Approach To Automate The Generation Of Radiotherapy Treatment Plans, Qian Li

Creative Activity and Research Day - CARD

The main goal of radiotherapy is to deliver a specified dose of radiation directly to the tumor while minimizing radiation damage to healthy tissues. Currently, the treatment plan is being developed by professional planners using a commercial treatment planning system. In this treatment planning system, the planner modifies the objectives and weights of the objectives until an ideal combination of doses is achieved. This arbitrary process can cost a few hours or a day to finish. My research aims to automate the generation of the plans by implementing an optimization algorithm on top of the treatment planning system using gradient …

Comparative Study Of Deep Learning Models For Network Intrusion Detection, Brian Lee, Sandhya Amaresh, Clifford Green, Daniel Engels

SMU Data Science Review

In this paper, we present a comparative evaluation of deep learning approaches to network intrusion detection. A Network Intrusion Detection System (NIDS) is a critical component of every Internet connected system due to likely attacks from both external and internal sources. A NIDS is used to detect network born attacks such as Denial of Service (DoS) attacks, malware replication, and intruders that are operating within the system. Multiple deep learning approaches have been proposed for intrusion detection systems. We evaluate three models, a vanilla deep neural net (DNN), self-taught learning (STL) approach, and Recurrent Neural Network (RNN) based Long Short …

Walknet: A Deep Learning Approach To Improving Sidewalk Quality And Accessibility, Andrew Abbott, Alex Deshowitz, Dennis Murray, Eric C. Larson

SMU Data Science Review

This paper proposes a framework for optimizing allocation of infrastructure spending on sidewalk improvement and allowing planners to focus their budgets on the areas in the most need. In this research, we identify curb ramps from Google Street View images using traditional machine learning and deep learning methods. Our convolutional neural network approach achieved an 83% accuracy and high level of precision when classifying curb cuts. We found that as the model received more data, the accuracy increased, which with the continued collection of crowdsourced labeling of curb cuts will increase the model’s classification power. We further investigated a model …

Cognitive Virtual Admissions Counselor, Kumar Raja Guvindan Raju, Cory Adams, Raghuram Srinivas

SMU Data Science Review

Abstract. In this paper, we present a cognitive virtual admissions counselor for the Master of Science in Data Science program at Southern Methodist University. The virtual admissions counselor is a system capable of providing potential students accurate information at the time that they want to know it. After the evaluation of multiple technologies, Amazon’s LEX was selected to serve as the core technology for the virtual counselor chatbot. Student surveys were leveraged to collect and generate training data to deploy the natural language capability. The cognitive virtual admissions counselor platform is currently capable of providing an end-to-end conversational dialog to …

Efficient Reduced Bias Genetic Algorithm For Generic Community Detection Objectives, Aditya Karnam Gururaj Rao

Theses

The problem of community structure identification has been an extensively investigated area for biology, physics, social sciences, and computer science in recent years for studying the properties of networks representing complex relationships. Most traditional methods, such as K-means and hierarchical clustering, are based on the assumption that communities have spherical configurations. Lately, Genetic Algorithms (GA) are being utilized for efficient community detection without imposing sphericity. GAs are machine learning methods which mimic natural selection and scale with the complexity of the network. However, traditional GA approaches employ a representation method that dramatically increases the solution space to be searched by …

Sensor Technologies For Intelligent Transportation Systems, Juan Guerrero-Ibáñez, Sherali Zeadally, Juan Contreras-Castillo

Information Science Faculty Publications

Modern society faces serious problems with transportation systems, including but not limited to traffic congestion, safety, and pollution. Information communication technologies have gained increasing attention and importance in modern transportation systems. Automotive manufacturers are developing in-vehicle sensors and their applications in different areas including safety, traffic management, and infotainment. Government institutions are implementing roadside infrastructures such as cameras and sensors to collect data about environmental and traffic conditions. By seamlessly integrating vehicles and sensing devices, their sensing and communication capabilities can be leveraged to achieve smart and intelligent transportation systems. We discuss how sensor technology can be integrated with the …

Husky Masquerade, Amila D. Desilva, Bryant A. Julstrom

Huskies Showcase

Award for "Best Demonstration".

Abstract

Face detection is the process where machines identify faces within an image or visual field. Face detection is used in analyzing emotions, and even in social networking applications, such as Snapchat. The underlying mechanism of face detection is to locate key landmarks on a person’s face. The goal is to detect faces using a webcam, find the facial landmarks of the detected faces, and overlay customized images relative to the facial landmarks. Machines need to be taught to detect faces. It is crucial to teach the program to identify the different types of jawlines. The …

User-Centric Privacy Preservation In Mobile And Location-Aware Applications, Mingming Guo

FIU Electronic Theses and Dissertations

The mobile and wireless community has brought a significant growth of location-aware devices including smart phones, connected vehicles and IoT devices. The combination of location-aware sensing, data processing and wireless communication in these devices leads to the rapid development of mobile and location-aware applications. Meanwhile, user privacy is becoming an indispensable concern. These mobile and location-aware applications, which collect data from mobile sensors carried by users or vehicles, return valuable data collection services (e.g., health condition monitoring, traffic monitoring, and natural disaster forecasting) in real time. The sequential spatial-temporal data queries sent by users provide their location trajectory information. The …

Pelee: A Real-Time Object Detection System On Mobile Devices, Jun Wang

Electronic Thesis and Dissertation Repository

There has been a rising interest in running high-quality Convolutional Neural Network (CNN) models under strict constraints on memory and computational budget. A number of efficient architectures have been proposed in recent years, for example, MobileNet, ShuffleNet, and NASNet-A. However, all these architectures are heavily dependent on depthwise separable convolution which lacks efficient implementation in most deep learning frameworks. Meanwhile, there are few studies that combine efficient models with fast object detection algorithms. This research tries to explore the design of an efficient CNN architecture for both image classification tasks and object detection tasks. We propose an efficient architecture named …

Topical Analysis Of The Enron Emails Using Graph Theory, Casey Kalinowski

Student Scholar Showcase

The Enron Scandal of the early 2000s shook the financial world. The subsequent investigation of the Enron Corporation resulted in the arrests of many top-level executives, but are these employees the only ones responsible for the wide scale fraud in the company? A topical analysis of a social network of over 150 employees of the Enron Corporation using Graph Theory could result in new findings or prove that the investigators were correct in their original findings. The research is a retrospective analysis of a corpus of over 500,000 emails from more than 150 employees and top-level executives of the Enron …

The Algorithmic Composition Of Classical Music Through Data Mining, Tom Donald Richmond, Imad Rahal

All College Thesis Program, 2016-2019

The desire to teach a computer how to algorithmically compose music has been a topic in the world of computer science since the 1950’s, with roots of computer-less algorithmic composition dating back to Mozart himself. One limitation of algorithmically composing music has been the difficulty of eliminating the human intervention required to achieve a musically homogeneous composition. We attempt to remedy this issue by teaching a computer how the rules of composition differ between the six distinct eras of classical music by having it examine a dataset of musical scores, rather than explicitly telling the computer the formal rules of …

Near-Optimal Control Of Switched Systems With Continuous-Time Dynamics Using Approximate Dynamic Programming, Tohid Sardarmehni

Mechanical Engineering Research Theses and Dissertations

Optimal control is a control method which provides inputs that minimize a performance index subject to state or input constraints [58]. The existing solutions for finding the exact optimal control solution such as Pontryagin’s minimum principle and dynamic programming suffer from curse of dimensionality in high order dynamical systems. One remedy for this problem is finding near optimal solution instead of the exact optimal solution to avoid curse of dimensionality [31]. A method for finding the approximate optimal solution is through Approximate Dynamic Programming (ADP) methods which are discussed in the subsequent chapters.

In this dissertation, optimal switching in switched …

Similarity Based Classification Of Adhd Using Singular Value Decomposition, Taban Eslami, Fahad Saeed

Parallel Computing and Data Science Lab Technical Reports

Attention deficit hyperactivity disorder (ADHD) is one of the most common brain disorders among children. This disorder is considered as a big threat for public health and causes attention, focus and organizing difficulties for children and even adults. Since the cause of ADHD is not known yet, data mining algorithms are being used to help discover patterns which discriminate healthy from ADHD subjects. Numerous efforts are underway with the goal of developing classification tools for ADHD diagnosis based on functional and structural magnetic resonance imaging data of the brain. In this paper, we used Eros, which is a technique for …

Artificial Intelligence: An Analysis Of Alan Turing’S Role In The Conception And Development Of Intelligent Machinery, Erika L. Furtado

Selected Honors Theses

The purpose of this thesis is to follow the thread of Alan Turing’s ideas throughout his decades of research and analyze how his predictions have come to fruition over the years. Turing’s Computing Machinery and Intelligence is the paper in which the Turing Test is described as an alternative way to answer the question “can machines think?” (Turing 433). Since the development of Turing’s original paper, there has been a tremendous amount of advancement in the field of artificial intelligence. The field has made its way into art classification as well as the medical industry. The main concept researched in …

Understanding Natural Keyboard Typing Using Convolutional Neural Networks On Mobile Sensor Data, Travis Siems

Computer Science and Engineering Theses and Dissertations

Mobile phones and other devices with embedded sensors are becoming increasingly ubiquitous. Audio and motion sensor data may be able to detect information that we did not think possible. Some researchers have created models that can predict computer keyboard typing from a nearby mobile device; however, certain limitations to their experiment setup and methods compelled us to be skeptical of the models’ realistic prediction capability. We investigate the possibility of understanding natural keyboard typing from mobile phones by performing a well-designed data collection experiment that encourages natural typing and interactions. This data collection helps capture realistic vulnerabilities of the security …