Artificial Intelligence and Robotics Commons^™

Computer-Aided Diagnosis Of Low Grade Endometrial Stromal Sarcoma (Lgess), Xinxin Yang

Master's Projects

Low grade endometrial stromal sarcoma (LGESS) is rare form of cancer, account- ing for about 0.2% of all uterine cancer cases. Approximately 75% of LGESS patients are initially misdiagnosed with leiomyoma, which is a type of benign tumor that is also known as fibroids. In this research, uterine tissue biopsy images of potential LGESS patients are preprocessed using segmentation and staining normalization algorithms. A wide variety of classic machine learning and leading deep learning models are then applied to classify tissue images as either benign or cancerous. For classic techniques, the highest classification accuracy we attain is 85%, while our …

Hidden Markov Model-Based Clustering For Malware Classification, Shamli Singh

Master's Projects

Automated techniques to classify malware samples into their respective families are critical in cybersecurity. Previously research applied ��-means clustering to scores generated by hidden Markov models (HMM) as a means of dealing with the malware classification problem. In this research, we follow a somewhat similar approach, but instead of using HMMs to generate scores, we directly cluster the HMMs themselves. We obtain good results on a challenging malware dataset.

Classifying Illegal Advertisements On The Darknet Using Nlp, Karan Shashin Shah

Master's Projects

The Darknet has become a place to conduct various illegal activities like child labor, contract murder, drug selling while staying anonymous. Traditionally, international and government agencies try to control these activities, but most of those actions are manual and time-consuming. Recently, various researchers developed Machine Learning (ML) approaches trying to aid in the process of detecting illegal activities. The above problem can benefit by using different Natural Language Processing (NLP) techniques. More specifically, researchers have used various classical topic modeling techniques like bag of words, N-grams, Term Frequency, Term Frequency Inverse Document Frequency (TF-IDF) to represent features and train machine …

Fake Malware Classification With Cnn Via Image Conversion: A Game Theory Approach, Yash Sahasrabuddhe

Master's Projects

Improvements in malware detection techniques have grown significantly over the past decade. These improvements have resulted in better security for systems from various forms of malware attacks. However, it is also the reason for continuous evolution of malware which makes it harder for current security mechanisms to detect them. Hence, there is a need to understand different malwares and study classification techniques using the ever-evolving field of machine learning. The goal of this research project is to identify similarities between malware families and to improve on classification of malwares within different malware families by implementing Convolutional Neural Networks (CNNs) on …

Keystroke Dynamics For User Authentication With Fixed And Free Text, Jianwei Li

Master's Projects

YouTube videos often include captivating descriptions and intriguing thumbnails designed to increase the number of views, and thereby increase the revenue for the person who posted the video. This creates an incentive for people to post clickbait videos, in which the content might deviate significantly from the title, description, or thumbnail. In effect, users are tricked into clicking on clickbait videos. In this research, we consider the challenging problem of detecting clickbait YouTube videos. We experiment with multiple state of the art machine learning techniques and a variety of textual features.

Image-Based Real Estate Appraisal Using Cnns And Ensemble Learning, Prathamesh Dnyanesh Kumkar

Master's Projects

Real Estate Appraisal is performed to evaluate properties during a range of activities like buying, selling, mortgaging, or insuring. Traditionally, this process is done by real estate brokers who consider factors like the location of a house, its area, the number of bedrooms and bathrooms, along with other amenities to assess the property. This approach is quite subjective since different brokers may arrive at a different quote for the same property depending on their analysis. The development in machine learning algorithms has given rise to several Automated Valuation Models (AVMs) to estimate real estate prices. Real estate websites use such …

Translating Natural Language Queries To Sparql, Shreya Satish Bhajikhaye

Master's Projects

The Semantic Web is an extensive knowledge base that contains facts in the form of RDF
triples. These facts are not easily accessible to the average user because to use them requires
an understanding of ontologies and a query language like SPARQL. Question answering systems
form a layer of abstraction on linked data to overcome these issues. These systems allow the
user to input a question in a natural language and receive the equivalent SPARQL query. The
user can then execute the query on the database to fetch the desired results. The standard
techniques involved in translating natural language questions …

Detecting And Predicting Visual Affordance Of Objects In A Given Environment, Bhumika Kaur Matharu

Master's Projects

The rapid growth of the development of autonomous robots is transforming the manufacturing and healthcare industry in many ways, but they still face many challenges. One of the challenges experienced by autonomous robots is their inability to manipulate an unknown object without human supervision. One way through which autonomous robots can manipulate an unknown object is affordance learning [1]. Affordance describes the action a user can perform on the object in given surroundings. This report describes our proposed model to detect and predict the affordance of an object from videos by leveraging the spatial-temporal feature extraction through ConvLSTM and Fully …

Machine Learning Using Serverless Computing, Vidish Naik

Master's Projects

Machine learning has been trending in the domain of computer science for quite some time. Newer and newer models and techniques are being developed every day. The adoption of cloud computing has only expedited the process of training machine learning. With its variety of services, cloud computing provides many options for training machine learning models. Leveraging these services is up to the user. Serverless computing is an important service offered by cloud service providers. It is useful for short tasks that are event-driven or periodic. Machine learning training can be divided into short tasks or batches to take advantage of …

A Hybrid Gaze Pointer With Voice Control, Indhuja Ravi

Master's Projects

Accessibility in technology has been a challenge since the beginning of the 1800s. Starting with building typewriters for the blind by Pellegrino Turri to the on-screen keyboard built by Microsoft, there have been several advancements towards assistive technologies. The basic tools necessary for anyone to operate a computer are to be able to navigate the device, input information, and perceive the output. All these three categories have been undergoing tremendous advancements over the years. Especially, with the internet boom, it has now become a necessity to point onto a computer screen. This has somewhat attracted research into this particular area. …

Automating Text Encapsulation Using Deep Learning, Anket Sah

Master's Projects

Data is an important aspect in any form be it communication, reviews, news articles, social media data, machine or real-time data. With the emergence of Covid-19, a pandemic seen like no other in recent times, information is being poured in from all directions on the internet. At times it is overwhelming to determine which data to read and follow. Another crucial aspect is separating factual data from distorted data that is being circulated widely. The title or short description of this data can play a key role. Many times, these descriptions can deceive a user with unwanted information. The user …

Defending Vehicles Against Cyberthreats: Challenges And A Detection-Based Solution, Qilin Liu

Master's Projects

The lack of concern with security when vehicular network protocols were designed some thirty years ago is about to take its toll as vehicles become more connected and smart. Today as demands for more functionality and connectivity on vehicles continue to grow, a plethora of Electronic Control Units (ECUs) that are able to communicate to external networks are added to the automobile networks. The proliferation of ECU and the increasing autonomy level give drivers more control over their vehicles and make driving easier, but at the same time they expand the attack surface, bringing more vulnerabilities to vehicles that might …

American Sign Language Assistant, Charulata Lodha

Master's Projects

Our implementation of a prototype computer vision system to help the deaf and mute
communicate in a shopping setting. Our system uses live video feeds to recognize American Sign Language (ASL) gestures and notify shop clerks of deaf and mute patrons’ intents. It generates a video dataset in the Unity Game Engine of 3D humanoid models in a shop setting performing ASL signs. Our system uses OpenPose to detect and recognize the bone points of the human body
from the live feed. The system then represents the motion sequences as high dimensional skeleton joint point trajectories followed by a time-warping …

Visual And Lingual Emotion Recognition Using Deep Learning Techniques, Akshay Kajale

Master's Projects

Emotion recognition has been an integral part of many applications like video games, cognitive computing, and human computer interaction. Emotion can be recognized by many sources including speech, facial expressions, hand gestures and textual attributes. We have developed a prototype emotion recognition system using computer vision and natural language processing techniques. Our goal hybrid system uses mobile camera frames and features abstracted from speech named Mel Frequency Cepstral Coefficient (MFCC) to recognize the emotion of a person. To acknowledge the emotions based on facial expressions, we have developed a Convolutional Neural Network (CNN) model, which has an accuracy of 68%. …

Year-Independent Prediction Of Food Insecurity Using Classical & Neural Network Machine Learning Methods, Caleb Christiansen, Torrey J. Wagner, Brent Langhals

Faculty Publications

Current food crisis predictions are developed by the Famine Early Warning System Network, but they fail to classify the majority of food crisis outbreaks with model metrics of recall (0.23), precision (0.42), and f1 (0.30). In this work, using a World Bank dataset, classical and neural network (NN) machine learning algorithms were developed to predict food crises in 21 countries. The best classical logistic regression algorithm achieved a high level of significance (p < 0.001) and precision (0.75) but was deficient in recall (0.20) and f1 (0.32). Of particular interest, the classical algorithm indicated that the vegetation index and the food price index were both positively correlated with food crises. A novel method for performing an iterative multidimensional hyperparameter search is presented, which resulted in significantly improved performance when applied to this dataset. Four iterations were conducted, which resulted in excellent 0.96 for metrics of precision, recall, and f1. Due to this strong performance, the food crisis year was removed from the dataset to prevent immediate extrapolation when used on future data, and the modeling process was repeated. The best “no year” model metrics remained strong, achieving ≥0.92 for recall, precision, and f1 while meeting a 10% f1 overfitting threshold on the test (0.84) and holdout (0.83) datasets. The year-agnostic neural network model represents a novel approach to classify food crises and outperforms current food crisis prediction efforts.

Experience-Driven Control For Networking And Computing, Zhiyuan Xu

Dissertations - ALL

Modern networking and computing systems have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this thesis, we aim to study system control problems from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL), to develop experience-driven model-free approaches, which enable a network or a device to learn the best way to control itself from its own experience (e.g., runtime statistics data) rather than from accurate mathematical models, just as a human learns a new skill (e.g., driving, swimming, etc). To demonstrate the feasibility and superiority of this experience-driven control design …

Experience-Driven Control For Networking And Computing, Zhiyuan Xu

Dissertations - ALL

Modern networking and computing systems have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this thesis, we aim to study system control problems from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL), to develop experience-driven model-free approaches, which enable a network or a device to learn the best way to control itself from its own experience (e.g., runtime statistics data) rather than from accurate mathematical models, just as a human learns a new skill (e.g., driving, swimming, etc). To demonstrate the feasibility and superiority of this experience-driven control design …

Human/Artificial Intelligence Coordination In Video Games, Michael Rodriguez

ART 108: Introduction to Games Studies

The emergence of video games has led to widespread inventions to enhance the reality of the experience. As a result, Artificial Intelligence (A.I.) was developed to create virtual experiences and attract a variety of players of video games. This paper will discuss video games in the context of Human-A.I. interaction and the importance of human coordination in video games. Unprecedented errors have been a common challenge in this relationship. An excellent example of these algorithms include population-based training and self-play, which have gained a lot of interest in video games. A.I. technology has surpassed human ability because they are simply …

Improving Additional Adversarial Robustness For Classification, Michael Guo

McKelvey School of Engineering Graduate Student Theses & Dissertations

Although neural networks have achieved remarkable success on classification, adversarial robustness is still a significant concern. There are now a series of approaches for designing adversarial examples and methods to defending against them. This paper consists of two projects. In our first work, we propose an approach by leveraging cognitive salience to enhance additional robustness on top of these methods. Specifically, for image classification, we split an image into the foreground (salient region) and background (the rest) and allow significantly larger adversarial perturbations in the background to produce stronger attacks. Furthermore, we show that adversarial training with dual-perturbation attacks yield …

Deep Learning Predicts Chromosomal Instability From Histopathology Images, Zhuoran Xu, Akanksha Verma, Uska Naveed, Samuel F. Bakhoum, Pegah Khosravi, Olivier Elemento

Publications and Research

Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with cancer in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through a deep learning-based model. When applied to a cohort of 1,010 patients with breast cancer (Training set: n = 858, Test set: n = 152) from The Cancer Genome Atlas where 485 patients have high CIN status, our model accurately classified CIN status, achieving an area under the curve of 0.822 with 81.2% sensitivity and 68.7% specificity in …

Real-Time Monitoring Of Fdm 3d Printer For Fault Detection Using Machine Learning: A Bibliometric Study, Vaibhav Kisan Kadam, Satish Kumar, Arunkumar Bongale

Library Philosophy and Practice (e-journal)

Additive Manufacturing has wide application range including healthcare, Fashion, Manufacturing, Prototypes, Tooling etc. AM techniques are subjected to various defects that may be printing defects or anomalies in machine. There is gap between current AM techniques and smart manufacturing since current AM lacks in build sensors necessary for process monitoring and fault detection. Both of these issues can be solved by incorporating real-time monitoring into AM. So the study is carried out to identify recent work done in AM to improve current system. For this bibliometric study Scopus database is used, study is kept limited to year 2010-2021 and English …

A Highly-Parameterized Ensemble To Play Gin Rummy, Masayuki Nagai '22, Kavya Shrivastava '23, Kien Ta '22, Steven Bogaerts, Chad Byers

Computer Science Faculty publications

This paper describes the design and training of a computer Gin Rummy player. The system includes three main components to make decisions about drawing cards, discarding, and ending the game, with numerous parameters controlling behavior. In particular, an ensemble approach is explored in the discard decision. Finally, three sets of parameter tuning and performance experiments are analyzed.

Self-Supervised Learning For Fine-Grained Visual Categorization, Muhammad Maaz, Hanoona Abdul Rasheed, Dhanalaxmi Gaddam

Student Publications

Recent research in self-supervised learning (SSL) has shown its capability in learning useful semantic representations from images for classification tasks. Through our work, we study the usefulness of SSL for Fine-Grained Visual Categorization (FGVC). FGVC aims to distinguish objects of visually similar subcategories within a general category. The small inter-class, but large intra-class variations within the dataset makes it a challenging task. The limited availability of annotated labels for such fine-grained data encourages the need for SSL, where additional supervision can boost learning without the cost of extra annotations. Our baseline achieves 86.36% top-1 classification accuracy on CUB-200-2011 dataset by …

Stochastic Goal Recognition Design, Christabel Wayllace

McKelvey School of Engineering Graduate Student Theses & Dissertations

Goal Recognition Design (GRD) is the problem of finding the least amount of environment modifications to force an acting agent to reveal its goal as early as possible. Figuring out an agent’s goal by observing its behavior is a problem studied in Psychology, Economics, and Artificial Intelligence, where it is known as goal recognition. Contrary to most common approaches where the focus is on finding faster algorithms to detect the goal, GRD takes an offline approach and focuses on environment design to facilitate goal recognition. This thesis investigates GRD problems when action outcomes are stochastic, which is the case of …

Machine Learning Methods For Depression Detection Using Smri And Rs-Fmri Images, Marzieh Sadat Mousavian

LSU Doctoral Dissertations

Major Depression Disorder (MDD) is a common disease throughout the world that negatively influences people’s lives. Early diagnosis of MDD is beneficial, so detecting practical biomarkers would aid clinicians in the diagnosis of MDD. Having an automated method to find biomarkers for MDD is helpful even though it is difficult. The main aim of this research is to generate a method for detecting discriminative features for MDD diagnosis based on Magnetic Resonance Imaging (MRI) data.

In this research, representational similarity analysis provides a framework to compare distributed patterns and obtain the similarity/dissimilarity of brain regions. Regions are obtained by either …

Quantifying Feature Overlaps In Deep Neural Networks And Their Applications In Unsupervised Learning And Generative Adversarial Networks, Edward Collier

LSU Doctoral Dissertations

Deep neural network learn a wide range of features from the input data. These features take many different forms from, structural to textural, and can be very scale invariant. The complexity of these features also differs from layer to layer. Much like the human brain, this behavior in deep neural networks can also be used to cluster and separate classes. Applicability in deep neural networks is the quantitative measurement of the networks ability to differentiate between clusters in feature space. Applicability can measure the differentiation between clusters of sets of classes, single classes, or even within the same class. In …

Automated Analysis Of Rfps Using Natural Language Processing (Nlp) For The Technology Domain, Sterling Beason, William Hinton, Yousri A. Salamah, Jordan Salsman

SMU Data Science Review

Much progress has been made in text analysis, specifically within the statistical domain of Term Frequency (TF) and Inverse Document Frequency (IDF). However, there is much room for improvement especially within the area of discovering Emerging Trends. Emerging Trend Detection Systems (ETDS) depend on ingesting a collection of textual data and TF/IDF to identify new or up-trending topics within the Corpus. However, the tremendous rate of change and the amount of digital information presents a challenge that makes it almost impossible for a human expert to spot emerging trends without relying on an automated ETD system. Since the U.S. Government …

Reinforcement Learning For Realistic Robotic Training: A Survey, Andres Jaramillo

Honors Scholar Theses

Reinforcement learning is a widely popular topic that has resulted in a plethora of

research papers and interest from academia and industry. When applied with robotics,

the field has showed some promising signs that robots can achieve levels of complex

cognitive abilities rivaling humans, but the goal of creating sapient robots is far from

a reality due to many challenges involved with training robots in a real world setting.

This paper will provide a survey regarding the keys towards realistic robotic training by

detailing the challenges and overviewing the reinforcement learning solutions involved

in getting a robot to think like …

Towards Open World Object Detection, K. J. Joseph, Salman Khan, Fahad Shahbaz Khan, Vineeth N. Balasubramanian

Computer Vision Faculty Publications

Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This motivates us to propose a novel computer vision problem called: 'Open World Object Detection', where a model is tasked to: 1) identify objects that have not been introduced to it as 'unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received. We formulate the problem, introduce a strong evaluation protocol …

Airbnb Price Prediction With Sentiment Classification, Peilu Liu

Master's Projects

Airbnb is an online platform that provides arrangements for short-term local home renting services. It is a challenging task for the house owner to price a rental home and attract customers. Customers also need to evaluate the price of the rental property based on the listing details. This paper demonstrates several existing Airbnb price prediction models using machine learning and external data to improve the prediction accuracy. It also discusses machine learning and neural network models that are commonly used for price prediction. The goal of this paper is to build a price prediction model using machine learning and sentiment …