Engineering Commons^™

How Visual Stimuli Evoked P300 Is Transforming The Brain–Computer Interface Landscape: A Prisma Compliant Systematic Review, Jai Kalra, Prashasti Mittal, Nirmiti Mittal, Abhishek Arora, Utkarsh Tewari, Aviral Chharia, Rahul Upadhyay, Vinay Kumar, Luca Longo

Articles

Non-invasive Visual Stimuli evoked-EEGbased P300 BCIs have gained immense attention in recent years due to their ability to help patients with disability using BCI-controlled assistive devices and applications. In addition to the medical field, P300 BCI has applications in entertainment, robotics, and education. The current article systematically reviews 147 articles that were published between 2006-2021*. Articles that pass the pre-defined criteria are included in the study. Further, classification based on their primary focus, including article orientation, participants’ age groups, tasks given, databases, the EEG devices used in the studies, classification models, and application domain, is performed. The application-based classification considers …

Ontology-Based Case Study Management Towards Bridging Training And Actual Investigation Gaps In Digital Forensics, Hung Q. Ngo, Nhien-An Le-Khac

Articles

The training programs in digital forensics have contributed many case study models to guide digital forensic analyses. However, they only account for a small number of real cases and they are usually too abstract while actual cybercrime investigations are more diverse and complex. This gap leads to difficulties in giving immediate and straightforward actions for law enforcement during cybercrime investigations. In this paper, we propose an ontology-based knowledge map model, which is a foundation model for building a case study management system for Digital Forensic Intelligence (DFINT) and Open Source Intelligence (OSINT) in digital forensics. The main idea of this …

Group-Invariant Reinforcement Learning, Fnu Ankur

Master's Theses

Our work introduces a way to learn an optimal reinforcement learning agent accompanied by intrinsic properties of the environment. The extracted properties helps the agent to extrapolate the learning to unseen states efficiently. Out of all the various types of properties, we are intrigued towards equivariant and invariant properties, which essentially translates to symmetry. Contrary to many approaches, we do not assume the symmetry, rather learn them, making the approach agnostic to the environment and the property. The learned properties offers multiple perspective of the environment to exploit it to benefit decision making while interacting with the environment. By building …

Automatic Presentation Slide Generation Using Llms, Tanya Gupta

Master's Theses

Presentation slides are widely used for conveying information in academic and professional contexts. However, manual slide creation can be time-consuming. Our research focuses on automated slide generation, specifically for scientific research papers. Automating the creation of presentation slides for scientific documents is a rather novel task and hence, there’s limited training data available and there also exists the token constraints of language models like BERT, with a maximum sequence length of 512 tokens. In this study, we fine-tune large language models, including Longformer-Encoder-Decoder (supporting sequences up to 16,834 tokens) and BIGBIRD-Pegasus (supporting sequences up to 4,096 tokens). We tackle this …

Deep Learning In Ai Medical Imaging For Stroke Diagnosis, James Mario Guzman

Master's Theses

Enhancing medical imaging stroke diagnosis applications with artificial intelligence (AI) tools to determine lesion volume, location and clinical metadata is vital toward guiding patient treatment and procedure. A major hardship in developing stroke diagnosis AI tools is the scarcity of publicly available clinical 3D stroke datasets. Through working with Johns Hopkins University, University of Michigan’s ICPSR data repository and SJSU research, we gained access to potentially the largest 3D MRI stroke dataset with clinical metadata annotated by neuroradiologists known as ICPSR 38464. With the ICPSR 38464 dataset recently being available through institutional review board (IRB) approval or exemption, we were …

Detecting The Onion Routing Traffic In Real-Time By Using Reinforcement Learning, Dazhou Liu

Master's Theses

Anonymous networks have been popularly utilized to protect user anonymity and facilitate network security for a decade. However, such networks have been a platform for adversarial affairs and various network attacks including suspicious traffic generators. As a result, detecting anonymous network traffic is one critical task to defend a network against unpredictable attacks. Many new methods using machine learning and deep learning techniques have been proposed. However, many of them rely heavily on a vast amount of labeled data and have complicated architectures. Since network traffic always fluctuates under different network environments, those techniques may degrade in performance due to …

Controllability-Constrained Deep Neural Network Models For Enhanced Control Of Dynamical Systems, Suruchi Sharma

Master's Theses

Control of a dynamical system without the knowledge of dynamics is an important and challenging task. Modern machine learning approaches, such as deep neural networks (DNNs), allow for the estimation of a dynamics model from control inputs and corresponding state observation outputs. Such data-driven models are often utilized for the derivation of model-based controllers. However, in general, there are no guarantees that a model represented by DNNs will be controllable according to the formal control-theoretical meaning of controllability, which is crucial for the design of effective controllers. This often precludes the use of DNN-estimated models in applications, where formal controllability …

Intrinsic Motivation By The Principles Of Non-Linear Dynamical Systems, Phu C. Nguyen

Master's Theses

The design of appropriate control rules for the stabilization of dynamical systems can require quite substantial domain knowledge. Modern AI methodologies, such as Reinforcement Learning, are often used to mitigate the need for such knowledge. However, these can be slow and often rely on at least some hand-designed reward structure, and thus human input, to be more effective. Here, we propose an alternative route to construct rewards requiring only minimal domain knowledge, essentially relying on the structure of the dynamical system itself. For this, we use truncated Lyapunov exponents as rewards to calculate the stabilizing controller from samples. Concretely, the …

Evaluation Of Lidar Uncertainty And Applications Towards Slam In Off-Road Environments, Zachary D. Jeffries

Dissertations, Master's Theses and Master's Reports

Safe and robust operation of autonomous ground vehicles in all types of conditions and environment necessitates complex perception systems and unique, innovative solutions. This work addresses automotive lidar and maximizing the performance of a simultaneous localization and mapping stack. An exploratory experiment and an open benchmarking experiment are both presented. Additionally, a popular SLAM application is extended to use the type of information gained from lidar characterization, demonstrating the performance gains and necessity to tightly couple perception software and sensor hardware. The first exploratory experiment collects data from child-sized, low-reflectance targets over a range from 15 m to 35 m. …

Neuromorphic Computing Applications In Robotics, Noah Zins

Dissertations, Master's Theses and Master's Reports

Deep learning achieves remarkable success through training using massively labeled datasets. However, the high demands on the datasets impede the feasibility of deep learning in edge computing scenarios and suffer from the data scarcity issue. Rather than relying on labeled data, animals learn by interacting with their surroundings and memorizing the relationships between events and objects. This learning paradigm is referred to as associative learning. The successful implementation of associative learning imitates self-learning schemes analogous to animals which resolve the challenges of deep learning. Current state-of-the-art implementations of associative memory are limited to simulations with small-scale and offline paradigms. Thus, …

Using Machine Learning To Identify Patterns In Learner-Submitted Code For The Purpose Of Assessment, Botond Tarcsay, Fernando Perez-Tellez, Jelena Vasic

Conference papers

Programming has become an important skill in today’s world and is taught widely both in traditional and online settings. Instructors need to grade increasing amounts of student work. Unit testing can contribute to the automation of the grading process but it cannot assess the structure or partial correctness of code, which is needed for finely differentiated grading. This paper builds on previous research that investigated machine learning models for determining the correctness of programs from token-based features of source code and found that some such models can be successful in classifying source code with respect to whether it passes unit …

การจำลองกำหนดการเดินเรือโดยใช้ไทม์ออโตมาตาแบบที่มีความน่าจะเป็น, รัตชนก เธียรปุญญธนากุล

Chulalongkorn University Theses and Dissertations (Chula ETD)

ในอุตสาหกรรมการขนส่งทางทะเลที่มีการจัดการด้านความเสี่ยงในการเกิดความล่าช้าในการเดินเรือตามกำหนดเป็นปัญหาที่ซับซ้อน และเกิดความเสี่ยงและเกิดค่าเสียหายผลจากถึงกำหนดล่าช้าที่จะต้องประสบกับค่าใช้จ่ายของต้นทุนที่สูงขึ้นจากปัญหาความล่าช้า จึงให้ความสนใจที่ปัญหาเหล่านี้อยู่ที่การให้ความสำคัญกับความน่าจะเป็นจากความไม่แน่นอนและเวลาในการเดินเรือ ซึ่งเป็นปัจจัยที่สำคัญในการวางแผนและจัดการตารางเดินเรือให้เหมาะสมและมีประสิทธิภาพและเหมาะสมกับเงื่อนไขและปัจจัยที่แปรผันในอุตสาหกรรมการขนส่งทางทะเล งานวิจัยนี้ จึงเล็งเห็นความสำคัญของการนำไทม์ออโตมาตาแบบที่มีความน่าจะเป็น Probabilistic Timed Automata (PTA) มาใช้ในการจำลองกำหนดการตารางเดินเรือ (Vessel Scheduling) เพื่อช่วยให้สามารถจำลองและประเมินผลของปัจจัยต่าง ๆ ที่ส่งผลต่อการเดินเรือได้อย่างเป็นระบบ และการช่วยให้ผู้วางแผนสามารถทำการปรับปรุงและวิเคราะห์ตารางเดินเรือ โดยมีผลจากการปรับปรุงค่าความนาจะเป็นและทำการทวนสอบผลที่ได้จากสถิติข้อมูลที่ใช้จำลองไม่เกิน 10% ผ่านการเขียนโปรแกรมด้วยภาษา PRISM โดยใช้ PRISM Model Checker โดยเครื่องมือสามารถจำลองพฤติกรรมการเดินเรือตามแบบจำลอง PTA ที่ออกแบบไว้ โดยคำนึงถึงปัจจัยของความน่าจะเป็นที่ส่งผลให้เกิดความล่าช้าและทำการทวนสอบด้วยสูตร PCTL ได้

Image Steganography Based On Chaoticfunction Andrandomize Function, Rusul Mansoor Al-Amri, Dalal N. Hamood, Alaa Kadhim Farhan

Iraqi Journal for Computer Science and Mathematics

The exchange of data is not limited to personal text information or information about institutions and governments, but includes digital mediatransferredvia the Internet includingeverything, whether texts, images or videosandaudio, or animation.These media need high-security protection and high speed during its transmission from one site to another. In this study, a new methodis suggestedfor hiding a gray-level image within a larger color imagebased on theproposed steganography mapthatmergedchaoticfunctionand randomize function. The size of the chaos and randomize functionsis16 bytes. Experimental resultsobtained a successful method based on mean squarederror, signal-to-noise ratio,peak signal noise rate, embedding capacity, entropy, and histogram. This method can rapidlyhideandextractciphertext …

An Optimized And Scalable Blockchain-Based Distributed Learning Platform For Consumer Iot, Zhaocheng Wang, Xueying Liu, Xinming Shao, Abdullah Alghamdi, Md. Shirajum Munir, Sujit Biswas

School of Cybersecurity Faculty Publications

Consumer Internet of Things (CIoT) manufacturers seek customer feedback to enhance their products and services, creating a smart ecosystem, like a smart home. Due to security and privacy concerns, blockchain-based federated learning (BCFL) ecosystems can let CIoT manufacturers update their machine learning (ML) models using end-user data. Federated learning (FL) uses privacy-preserving ML techniques to forecast customers' needs and consumption habits, and blockchain replaces the centralized aggregator to safeguard the ecosystem. However, blockchain technology (BCT) struggles with scalability and quick ledger expansion. In BCFL, local model generation and secure aggregation are other issues. This research introduces a novel architecture, emphasizing …

Robustembed: Robust Sentence Embeddings Using Self-Supervised Contrastive Pre-Training, Javad Asl, Eduardo Blanco, Daniel Takabi

School of Cybersecurity Faculty Publications

Pre-trained language models (PLMs) have demonstrated their exceptional performance across a wide range of natural language processing tasks. The utilization of PLM-based sentence embeddings enables the generation of contextual representations that capture rich semantic information. However, despite their success with unseen samples, current PLM-based representations suffer from poor robustness in adversarial scenarios. In this paper, we propose RobustEmbed, a self-supervised sentence embedding framework that enhances both generalization and robustness in various text representation tasks and against diverse adversarial attacks. By generating high-risk adversarial perturbations to promote higher invariance in the embedding space and leveraging the perturbation within a novel contrastive …

Analysis Of Attention Mechanisms In Box-Embedding Systems, Jeffrey Sardina Jeffrey Sardina, Callie Sardina, John Kelleher, Declan O’Sullivan

Conference papers

Large-scale Knowledge Graphs (KGs) have recently gained considerable research attention for their ability to model the inter- and intra- relationships of data. However, the huge scale of KGs has necessitated the use of querying methods to facilitate human use. Question Answering (QA) systems have shown much promise in breaking down this human-machine barrier. A recent QA model that achieved state-of-the-art performance, Query2box, modelled queries on a KG using box embeddings with an attention mechanism backend to compute the intersections of boxes for query resolution. In this paper, we introduce a new model, Query2Geom, which replaces the Query2box attention mechanism with …

Action Classification In Human Robot Interaction Cells In Manufacturing, Shakra S.M. Mehak, Maria Chiara Leva, John Kelleher, Michael Guilfoyle

Conference papers

Action recognition has become a prerequisite approach to fluent Human-Robot Interaction (HRI) due to a high degree of movement flexibility. With the improvements in machine learning algorithms, robots are gradually transitioning into more human-populated areas. However, HRI systems demand the need for robots to possess enough cognition. The action recognition algorithms require massive training datasets, structural information of objects in the environment, and less expensive models in terms of computational complexity. In addition, many such algorithms are trained on datasets derived from daily activities. The algorithms trained on non-industrial datasets may have an unfavorable impact on implementing models and validating …

Developing A Web-Based System For Remote Collection And Analysis Of Vehicle Electrical Systems Over Canbus Using Carloop, Joshua N. Valle, Alex Columna-Fuentes

Capstone Showcase

Our program collects vehicle data using an OBD-II device called Carloop that is plugged into the vehicle's diagnostic port. The device executes our code which then communicates with the vehicle's onboard computer to collect data such as engine RPM, vehicle speed, fuel level, and other diagnostic information. This data is then sent over WiFi to Particle’s Cloud, which is a platform for managing IoT devices.

Integrations set up on Particle take care of sending data to our InfluxDB Database, which is hosted on our own cloud-based machine. InfluxDB is a high-performance time-series database that is optimized for storing and querying …

Evaluating Ai Sentiment Analysis, Aakriti Shah

Honors Program Theses

This paper presents a comparative analysis of human and AI performance on a sentiment analysis task involving the coding of qualitative data from community program transcripts. The results demonstrate promising but imperfect agreement between two AI models, Claude and Bing, versus three human annotators and one expert annotator using the Community Capitals framework categories. While both models achieved fair alignment with human judgment, confusion patterns emerged involving metaphorical language and text overlapping multiple categories. The findings provide a case study for benchmarking conversational AI systems against human baselines to reveal limitations and target improvements. Key gaps center around distinguishing between …

Graph Based System For Evidential Reasoning, Divyarajsinh Chauhan

Master's Projects

In the modern data driven world, graph editing tools have become very essential as they provide means to understand, visualize and manipulate complex relationships between various datasets. They have especially played a crucial role in the space of evidential reasoning, where it has made a significant impact in the decision making process by developers, analysts and researchers to understand and represent the connection in the data. Existing tools fail to handle huge amounts of data efficiently and also don’t have the features required to handle tasks related to evidential reasoning.To address these gaps, we developed Pygrapher Web UI tool. We …

Pygrapherconnect, Shubham Jain

Master's Projects

The evolving landscape of backend computational systems especially in biomedical research involving heavy data operations which have a gap of not being used properly. It is due to the lack of communication standard between the frontend and backend. This gap presents a problem to researchers who need to use the frontend for visualizing and manipulating their data but also want to do complex analysis. CAPRI a python-based backend system specializing in analyzing Evidential Reasoning data also has the same issue. This project offers a solution PyGrapherConnect module acting as a data conversion layer between CAPRI and PyGrapher, its frontend interface. …

Gesture Recognition With Deep Learning, Chaz Chang

Master's Projects

Gesture recognition is a machine learning and computer vision application where gestures are detected from videos. This project uses pose estimation to find the coordinates of important joints as a preprocessing step before trying to classify the gesture. Machine learning layers such as Convolutional Neural Network and Long Short-Term Memory are used. Various types of machine learning models are trained. The accuracy and f1 score of each model are compared. Feature selection is done by testing with different subsets of features. The results show that pose estimation as a preprocessing step provides good accuracy for gesture recognition. The results also …

Prediction Of 2024 Indian Pm Election Results Using Sentiment Analysis On Twitter Data, Surabhi Gupta

Master's Projects

This sentiments analysis study presents a methodical approach to predict the 2024 Indian Prime Minister Election. Data collected spanning from 2020 to 2023 from Twitter using hashtags such as IndianPMElection2024 and on topics such as the revocation of the special status of Jammu and Kashmir, the Farm Bill, and the Digital India initiative, form the core of this research. We utilized a combination of sentiment extraction tools-namely, the NLP Town's Bidirectional Encoder Representations from Transformers (BERT)-based multilingual uncased sentiment model, Valance Aware Dictionary for Sentiment Reasoning (VADER), and TextBlob. Additionally, we used a well-established machine learning model Naive Bayes, deep …

Mild Cognitive Impairment And Alzheimer’S Disease Detection And Testing Interface (Mci-Addti) Modeller10.4 Integrating Structure-Function Prediction Modules, Grant Galileo Jacobson

Master's Projects

In the population of adult human patients who over express Beta and Tau Amyloids, it is unclear why 40% of them do not have Alzheimer’s Disease (AD), when all patients with AD have an overexpression of Beta and Tau Amyloids. The MCI-AD-DTI project’s epigenetic pipeline is an evolving computation tool that seeks epigenetic-related information related to the observed disparity. The MCI-AD-DTI’s epigenetic pipeline’s ability to identify mutations currently relies solely on PyPDB for verification of its protein functionality evaluation. The assessment process of the industry standard application, Modeller10.4, is independent from the current epigenetic pipeline’s protein evaluation algorithm. Thus, this …

Multimap Implementation In Openjdk, Nishant Yadav

Master's Projects

A key-value pair is an elementary data model in which a unique key is associated with a given value. This association between the key and the value allows for a quick lookup of data based on the key and hence is extensively used in programming languages, NoSQL databases, caches, session management, etc. In Java OpenJDK, this elementary data model is implemented by the interface Map, which allows efficient storage and retrieval of data but can only store a single value against each key. In this project, we have implemented a MultiMap data structure in OpenJDK which allows associating multiple values …

Xai-Driven Cnn For Diabetic Retinopathy Detection, Vikas Shenoy Pete

Master's Projects

Diabetes, a chronic metabolic disorder, poses a significant health threat with potentially severe consequences, including diabetic retinopathy, a leading cause of blindness. In this project, we tackle this threat by developing a Convolutional Neural Network (CNN) to support the diagnosis based on eye images. The aim is early detection and intervention to mitigate the effects of diabetes on eye health. To enhance transparency and interpretability, we incorporate explainable AI techniques. This research not only contributes to the early diagnosis of diabetic eye disease but also advances our understanding of how deep learning models arrive at their decisions, fostering trust and …

Serverless Architecture For Machine Learning, Ikshaku Goswami

Master's Projects

Serverless computing is an area under cloud computing which does not require individual management of cloud infrastructure and services. It is the groundwork behind Function as a Service or FaaS cloud computing technique. FaaS provides a stateless event-driven orchestration of functions and services for applications deployed in the cloud, without having to manage the servers and other infrastructure resources. This event driven architecture is being well utilized to manage different web-applications and services. Machine learning can bring a unique challenge to serverless computing, as it involves high-intensive tasks which requires voluminous data. In such a scenario it becomes essential to …

Uncertainty-Aware And Explainable Artificial Intelligence For Identification Of Human Errors In Nuclear Power Plants, Bhavya Reddy Kotla

Master's Projects

Nuclear Power Plants (NPPs) can face challenges in maintaining standard operations due to a range of issues, including human mistakes, mechanical breakdowns, electrical problems, measurement errors, and external influences. Swift and precise detection of these issues is crucial for stabilizing the NPPs. Identifying such operational anomalies is complex due to the numerous potential scenarios. Additionally, operators need to promptly discern the nature of an incident by tracking various indicators, a process that can be mentally taxing and increase the likelihood of human errors. Inaccurate identification of problems leads to inappropriate corrective actions, adversely affecting the safety and efficiency of NPPs. …

A Natural Language Processing Approach To Malware Classification, Ritik Mehta

Master's Projects

Many different machine learning and deep learning techniques have been successfully employed for malware detection and classification. Examples of popular learning techniques in the malware domain include Hidden Markov Models (HMM), Random Forests (RF), Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Recurrent Neural Networks (RNN) such as Long Short-Term Memory (LSTM) networks. In this research, we consider a hybrid architecture, where HMMs are trained on opcode sequences, and the resulting hidden states of these trained HMMs are used as feature vectors in various classifiers. In this context, extracting the HMM hidden state sequences can be viewed as a …

Image-Based Classification Of Malware Using T-Sne Images, Vincent Stowbunenko

Master's Projects

This Master’s project proposes a novel technique for classifying malware using image-based methods. The approach involves generating t-SNE images from the EMBER dataset, which contains one million samples of both malware and benign files, each represented by over 2,000 features. The t-SNE technique is well-suited for capturing intricate patterns in complex datasets because it effectively maintains the local structure. These t-SNE images are then used as inputs to train two lightweight image classification models, SqueezeNet and MobileNet. Additionally, to provide a benchmark for comparison, a non-image classification model using LightGBM is also explored.

As part of the investigation, the project …