Engineering Commons^™

Cyber Attacks Against Industrial Control Systems, Adam Kardorff

LSU Master's Theses

Industrial Control Systems (ICS) are the foundation of our critical infrastructure, and allow for the manufacturing of the products we need. These systems monitor and control power plants, water treatment plants, manufacturing plants, and much more. The security of these systems is crucial to our everyday lives and to the safety of those working with ICS. In this thesis we examined how an attacker can take control of these systems using a power plant simulator in the Applied Cybersecurity Lab at LSU. Running experiments on a live environment can be costly and dangerous, so using a simulated environment is the …

Cyberinet: Integrated Semi-Modular Sensors For The Computer-Augmented Clarinet, Matthew Bardin

LSU Doctoral Dissertations

The Cyberinet is a new Augmented instrument designed to easily and intuitively provide a method of computer-enhanced performance to the Clarinetist to allow for greater control and expressiveness in a performance. A performer utilizing the Cyberinet is able to seamlessly switch between a traditional performance setting and an augmented one. Towards this, the Cyberinet is a hardware replacement for a portion of a Clarinet containing a variety of sensors embedded within the unit. These sensors collect various real time data motion data of the performer and air fow within the instrument. Additional sensors can be connected to the Cyberinet to …

An Investigation On The Resilience Of Long Short-Term Memory Deep Neural Networks, Christopher Vasquez

LSU Master's Theses

In a world of continuously advancing technology, the reliance on these technologies continues to increase. Recently, transformer networks [22] have been implemented through various projects such as ChatGPT. These networks are extremely computationally demanding and require cutting-edge hardware to explore. However, with the growing increase and popularity of these neural networks, a question of reliability and resilience comes about, especially as the dependency and research on these networks grow. Given the computational demand of transformer networks, we investigate the resilience of the weights and biases of the predecessor of these networks, i.e. the Long Short-Term (LSTM) neural network, through four …

Machine-Learning Approaches For Developing An Autograder For High School-Level Cs-For-All Initiatives, Sirazum Munira Tisha

LSU Doctoral Dissertations

Most existing autograders used for grading programming assignments are based on unit testing, which is tedious to implement for programs with graphical output and does not allow testing for other code aspects, such as programming style or structure. We present a novel autograding approach based on machine learning that can successfully check the quality of coding assignments from a high school-level CS-for-all computational thinking course. For evaluating our autograder, we graded 2,675 samples from five different assignments from the past three years, including open-ended problems from different units of the course curriculum. Our autograder uses features based on lexical analysis …

Enabling The Human Perception Of A Working Camera In Web Conferences Via Its Movement, Anish Shrestha

LSU Master's Theses

In recent years, video conferencing has seen a significant increase in its usage due to the COVID-19 pandemic. When casting user’s video to other participants, the videoconference applications (e.g. Zoom, FaceTime, Skype, etc.) mainly leverage 1) webcam’s LED-light indicator, 2) user’s video feedback in the software and 3) the software’s video on/off icons to remind the user whether the camera is being used. However, these methods all impose the responsibility on the user itself to check the camera status, and there have been numerous cases reported when users expose their privacy inadvertently due to not realizing that their camera is …

Device Free Indoor Localization Of Human Target Using Wifi Fingerprinting, Prasanga Neupane

LSU Master's Theses

Indoor localization of human objects has many important applications nowadays. Proposed here is a new device free approach where all the transceiver devices are fixed in an indoor environment so that the human target doesn't need to carry any transceiver device with them. This work proposes radio-frequency fingerprinting for the localization of human targets which makes this even more convenient as radio-frequency wireless signals can be easily acquired using an existing wireless network in an indoor environment. This work explores different avenues for optimal and effective placement of transmitter devices for better localization. In this work, an experimental environment is …

Machine Learning Assisted Discovery Of Shape Memory Polymers And Their Thermomechanical Modeling, Cheng Yan

LSU Doctoral Dissertations

As a new class of smart materials, shape memory polymer (SMP) is gaining great attention in both academia and industry. One challenge is that the chemical space is huge, while the human intelligence is limited, so that discovery of new SMPs becomes more and more difficult. In this dissertation, by adopting a series of machine learning (ML) methods, two frameworks are established for discovering new thermoset shape memory polymers (TSMPs). Specifically, one of them is performed by a combination of four methods, i.e., the most recently proposed linear notation BigSMILES, supplementing existing dataset by reasonable approximation, a mixed dimension (1D …

Efficient Information Retrieval For Software Bug Localization, Saket Khatiwada

LSU Doctoral Dissertations

Software systems are often shipped with defects. When a bug is reported, developers use the information available in the associated report to locate source code fragments that need to be modified to fix the bug. However, as software systems evolve in size and complexity, bug localization can become a tedious and time-consuming process. Contemporary bug localization tools utilize Information Retrieval (IR) methods for automated support to minimize the manual effort. IR methods exploit the textual content of bug reports to capture and rank relevant buggy source files. However, for an IR-based bug localization tool to be useful, it must achieve …

Interpretable And Anti-Bias Machine Learning Models For Human Event Sequence Data, Zihan Zhou

LSU Doctoral Dissertations

Growing volumes and varieties of human event sequence data are available in many applications such as recommender systems, social network, medical diagnosis, and predictive policing. Human event sequence data is usually clustered and exhibits self-exciting properties. Machine learning models especially deep neural network models have shown great potential in improving the prediction accuracy of future events. However, current approaches still suffer from several drawbacks such as model transparency, unfair prediction and the poor prediction accuracy due to data sparsity and bias. Another issue in modeling human event data is that data collected from real word is usually incomplete, and even …

Asynchronous, Distributed Optical Mutual Exclusion And Applications, Ahmed Bahaael Mansour

LSU Doctoral Dissertations

Silicon photonics have drawn much recent interest in the setting of intra-chip andmodule communication. In this dissertation, we address a fundamental computationalproblem, mutual exclusion, in the setting of optical interconnects. As a main result, wepropose an optical network and an algorithm for it to distribute a token (shared resource)mutually exclusively among a set ofnprocessing elements. Following a request, the tokenis granted in constant amortized time andO(n) worst case time; this assumes constantpropagation time for light within the chip. Additionally, the distribution of tokens is fair,ensuring that no token request is denied more thann−1 times in succession; this is thebest possible. …

An Approach To Counting Vehicles From Pre-Recorded Video Using Computer Algorithms, Mishuk Majumder

LSU Master's Theses

One of the fundamental sources of data for traffic analysis is vehicle counts, which can be conducted either by the traditional manual method or by automated means. Different agencies have guidelines for manual counting, but they are typically prepared for particular conditions. In the case of automated counting, different methods have been applied, but You Only Look Once (YOLO), a recently developed object detection model, presents new potential in automated vehicle counting. The first objective of this study was to formulate general guidelines for manual counting based on experience gained in the field. Another goal of this study was to …

Optimizing The Performance Of Multi-Threaded Linear Algebra Libraries Based On Task Granularity, Shahrzad Shirzad

LSU Doctoral Dissertations

Linear algebra libraries play a very important role in many HPC applications. As larger datasets are created everyday, it also becomes crucial for the multi-threaded linear algebra libraries to utilize the compute resources properly. Moving toward exascale computing, the current programming models would not be able to fully take advantage of the advances in memory hierarchies, computer architectures, and networks. Asynchronous Many-Task(AMT) Runtime systems would be the solution to help the developers to manage the available parallelism. In this Dissertation we propose an adaptive solution to improve the performance of a linear algebra library based on a set of compile-time …

Rfid Item-Level Tagging In A Grocery Store Environment, Brian Truman

LSU Master's Theses

The purpose of this research was to investigate how effective item-level Radio Frequency Identification (RFID) tagging would be using current RFID technology as a replacement for barcodes in a supermarket/grocery store environment.

To accomplish this, an experiment was be performed that utilized commercially available RFID technology. Passive Ultra High Frequency (UHF) RFID Tags were affixed to various grocery store items of different material categories (Food, Metal, Plastic, Liquid, and Glass), and placed in a metal shopping cart. Eight (8) antenna arrangements were created, comprised of different combinations of four (4) antennas in different locations around the cart.

The experiment was …

Effective Fuzzing Framework For The Sleuthkit Tools, Shravya Paruchuri

LSU Master's Theses

The fields of digital forensics and incident response have seen significant growth over the last decade due to the increasing threats faced by organizations and the continued reliance on digital platforms and devices by criminals. In the past, digital investigations were performed manually by expert investigators, but this approach has become no longer viable given the amount of data that must be processed compared to the relatively small number of trained investigators. These resource constraints have led to the development and reliance on automated processing and analysis systems for digital evidence. In this paper, we present our effort to develop …

Thermal-Kinect Fusion Scanning System For Bodyshape Inpainting And Estimation Under Clothing, Sirazum Munira Tisha

LSU Master's Theses

In today's interactive world 3D body scanning is necessary in the field of making virtual avatar, apparel industry, physical health assessment and so on. 3D scanners that are used in this process are very costly and also requires subject to be nearly naked or wear a special tight fitting cloths. A cost effective 3D body scanning system which can estimate body parameters under clothing will be the best solution in this regard. In our experiment we build such a body scanning system by fusing Kinect depth sensor and a Thermal camera. Kinect can sense the depth of the subject and …

Large-Scale Data Analysis And Deep Learning Using Distributed Cyberinfrastructures And High Performance Computing, Richard Dodge Platania

LSU Doctoral Dissertations

Data in many research fields continues to grow in both size and complexity. For instance, recent technological advances have caused an increased throughput in data in various biological-related endeavors, such as DNA sequencing, molecular simulations, and medical imaging. In addition, the variance in the types of data (textual, signal, image, etc.) adds an additional complexity in analyzing the data. As such, there is a need for uniquely developed applications that cater towards the type of data. Several considerations must be made when attempting to create a tool for a particular dataset. First, we must consider the type of algorithm required …

Distributed Wireless Algorithms For Rfid Systems: Grouping Proofs And Cardinality Estimation, Vanya D. Cherneva

LSU Doctoral Dissertations

The breadth and depth of the use of Radio Frequency Identification (RFID) are becoming more substantial. RFID is a technology useful for identifying unique items through radio waves. We design algorithms on RFID-based systems for the Grouping Proof and Cardinality Estimation problems.

A grouping-proof protocol is evidence that a reader simultaneously scanned the RFID tags in a group. In many practical scenarios, grouping-proofs greatly expand the potential of RFID-based systems such as supply chain applications, simultaneous scanning of multiple forms of IDs in banks or airports, and government paperwork. The design of RFID grouping-proofs that provide optimal security, privacy, and …

Effective Methods And Tools For Mining App Store Reviews, Nishant Jha

LSU Doctoral Dissertations

Research on mining user reviews in mobile application (app) stores has noticeably advanced in the past few years. The main objective is to extract useful information that app developers can use to build more sustainable apps. In general, existing research on app store mining can be classified into three genres: classification of user feedback into different types of software maintenance requests (e.g., bug reports and feature requests), building practical tools that are readily available for developers to use, and proposing visions for enhanced mobile app stores that integrate multiple sources of user feedback to ensure app survivability. Despite these major …

Distributed Iterative Graph Processing Using Nosql With Data Locality, Ayam Pokhrel

LSU Master's Theses

A tremendous amount of data is generated every day from a wide range of sources such as social networks, sensors, and application logs. Among them, graph data is one type that represents valuable relationships between various entities. Analytics of large graphs has become an essential part of business processes and scientific studies because it leads to deep and meaningful insights into the related domain based on the connections between various entities. However, the optimal processing of large-scale iterative graph computations is very challenging due to the issues like fault tolerance, high memory requirement, parallelization, and scalability. Most of the contemporary …

Image Processing Applications In Real Life: 2d Fragmented Image And Document Reassembly And Frequency Division Multiplexed Imaging, Houman Kamran Habibkhani

LSU Doctoral Dissertations

In this era of modern technology, image processing is one the most studied disciplines of signal processing and its applications can be found in every aspect of our daily life. In this work three main applications for image processing has been studied.

In chapter 1, frequency division multiplexed imaging (FDMI), a novel idea in the field of computational photography, has been introduced. Using FDMI, multiple images are captured simultaneously in a single shot and can later be extracted from the multiplexed image. This is achieved by spatially modulating the images so that they are placed at different locations in the …

Evaluating Classifiers' Optimal Performances Over A Range Of Misclassification Costs By Using Cost-Sensitive Classification, Ramy Al-Saffar

LSU Master's Theses

We believe that using the classification accuracy is not enough to evaluate the performances of classification algorithms. It can be misleading due to overlooking an important element which is the cost if classification is inaccurate. Furthermore, the Receiver Operational Characteristic (ROC) is one of the most popular graphs used to evaluate classifiers performances. However, one of the biggest ROC’s shortcomings is the assumption of equal costs for all misclassified data. Therefore, our goal is to reduce the total cost of decision making by selecting the classifier that has the least total misclassification cost. Nevertheless, the exact misclassification cost is usually …

Data-Driven Abstraction, Vivian Mankau Ho

LSU Master's Theses

Given a program analysis problem that consists of a program and a property of interest, we use a data-driven approach to automatically construct a sequence of abstractions that approach an ideal abstraction suitable for solving that problem. This process begins with an infinite concrete domain that maps to a finite abstract domain defined by statistical procedures resulting in a clustering mixture model. Given a set of properties expressed as formulas in a restricted and bounded variant of CTL, we can test the success of the abstraction with respect to a predefined performance level. In addition, we can perform iterative abstraction-refinement …

Compiler And Runtime Optimization Techniques For Implementation Scalable Parallel Applications, Zahra Khatami

LSU Doctoral Dissertations

The compiler is able to detect the data dependencies in an application and is able to analyze the specific sections of code for parallelization potential. However, all of these techniques provided by a compiler are usually applied at compile time, so they rely on static analysis, which is insufficient for achieving maximum parallelism and desired application scalability. These compiler techniques should consider both the static information gathered at compile time and dynamic analysis captured at runtime about the system to generate a safe parallel application. On the other hand, runtime information is often speculative. Solely relying on it doesn't guarantee …