Physical Sciences and Mathematics Commons^™

Class Activation Mapping And Uncertainty Estimation In Multi-Organ Segmentation, Md. Shibly Sadique, Walia Farzana, Ahmed Temtam, Khan Iftekharuddin, Khan Iftekharuddin (Ed.), Weijie Chen (Ed.)

Electrical & Computer Engineering Faculty Publications

Deep learning (DL)-based medical imaging and image segmentation algorithms achieve impressive performance on many benchmarks. Yet the efficacy of deep learning methods for future clinical applications may become questionable due to the lack of ability to reason with uncertainty and interpret probable areas of failures in prediction decisions. Therefore, it is desired that such a deep learning model for segmentation classification is able to reliably predict its confidence measure and map back to the original imaging cases to interpret the prediction decisions. In this work, uncertainty estimation for multiorgan segmentation task is evaluated to interpret the predictive modeling in DL …

Comparison Of Machine Learning Methods For Classification Of Alexithymia In Individuals With And Without Autism From Eye-Tracking Data, Furkan Iigin, Megan A. Witherow, Khan M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Alexithymia describes a psychological state where individuals struggle with feeling and expressing their emotions. Individuals with alexithymia may also have a more difficult time understanding the emotions of others and may express atypical attention to the eyes when recognizing emotions. This is known to affect individuals with Autism Spectrum Disorder (ASD) differently than neurotypical (NT) individuals. Using a public data set of eye-tracking data from seventy individuals with and without autism who have been assessed for alexithymia, we train multiple traditional machine learning models for alexithymia classification including support vector machines, logistic regression, decision trees, random forest, and multilayer perceptron. …

Special Section Editorial: Artificial Intelligence For Medical Imaging In Clinical Practice, Claudia Mello-Thoms, Karen Drukker, Sian Taylor-Phillips, Khan Iftekharuddin, Marios Gavrielides

Electrical & Computer Engineering Faculty Publications

This editorial introduces the JMI Special Section on Artificial Intelligence for Medical Imaging in Clinical Practice.

Light Auditor: Power Measurement Can Tell Private Data Leakage Through Iot Covert Channels, Woosub Jung, Kailai Cui, Kenneth Koltermann, Junjie Wang, Chunsheng Xin, Gang Zhou

Electrical & Computer Engineering Faculty Publications

Despite many conveniences of using IoT devices, they have suffered from various attacks due to their weak security. Besides well-known botnet attacks, IoT devices are vulnerable to recent covert-channel attacks. However, no study to date has considered these IoT covert-channel attacks. Among these attacks, researchers have demonstrated exfiltrating users' private data by exploiting the smart bulb's capability of infrared emission.

In this paper, we propose a power-auditing-based system that defends the data exfiltration attack on the smart bulb as a case study. We first implement this infrared-based attack in a lab environment. With a newly-collected power consumption dataset, we pre-process …

Security Of Internet Of Things (Iot) Using Federated Learning And Deep Learning — Recent Advancements, Issues And Prospects, Vinay Gugueoth, Sunitha Safavat, Sachin Shetty

Electrical & Computer Engineering Faculty Publications

There is a great demand for an efficient security framework which can secure IoT systems from potential adversarial attacks. However, it is challenging to design a suitable security model for IoT considering the dynamic and distributed nature of IoT. This motivates the researchers to focus more on investigating the role of machine learning (ML) in the designing of security models. A brief analysis of different ML algorithms for IoT security is discussed along with the advantages and limitations of ML algorithms. Existing studies state that ML algorithms suffer from the problem of high computational overhead and risk of privacy leakage. …

Adaptive Critic Network For Person Tracking Using 3d Skeleton Data, Joseph G. Zalameda, Alex Glandon, Khan M. Iftekharuddin, Mohammad S. Alam (Ed.), Vijayan K. Asari (Ed.)

Electrical & Computer Engineering Faculty Publications

Analysis of human gait using 3-dimensional co-occurrence skeleton joints extracted from Lidar sensor data has been shown a viable method for predicting person identity. The co-occurrence based networks rely on the spatial changes between frames of each joint in the skeleton data sequence. Normally, this data is obtained using a Lidar skeleton extraction method to estimate these co-occurrence features from raw Lidar frames, which can be prone to incorrect joint estimations when part of the body is occluded. These datasets can also be time consuming and expensive to collect and typically offer a small number of samples for training and …

Deep-Learning-Based Classification Of Digitally Modulated Signals Using Capsule Networks And Cyclic Cumulants, John A. Snoap, Dimitrie C. Popescu, James A. Latshaw, Chad M. Spooner

Electrical & Computer Engineering Faculty Publications

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper …

A Survey Of Using Machine Learning In Iot Security And The Challenges Faced By Researchers, Khawlah M. Harahsheh, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

The Internet of Things (IoT) has become more popular in the last 15 years as it has significantly improved and gained control in multiple fields. We are nowadays surrounded by billions of IoT devices that directly integrate with our lives, some of them are at the center of our homes, and others control sensitive data such as military fields, healthcare, and datacenters, among others. This popularity makes factories and companies compete to produce and develop many types of those devices without caring about how secure they are. On the other hand, IoT is considered a good insecure environment for cyber …

Development Of Machine Learning Based Approach To Predict Fuel Consumption And Maintenance Cost Of Heavy-Duty Vehicles Using Diesel And Alternative Fuels, Sasanka Katreddi

Graduate Theses, Dissertations, and Problem Reports

One of the major contributors of human-made greenhouse gases (GHG) namely carbon dioxide (CO2), methane (CH4), and nitrous oxide (NOX) in the transportation sector and heavy-duty vehicles (HDV) contributing to about 27% of the overall fraction. In addition to the rapid increase in global temperature, airborne pollutants from diesel vehicles also present a risk to human health. Even a small improvement that could potentially drive energy savings to the century-old mature diesel technology could yield a significant impact on minimizing greenhouse gas emissions. With the increasing focus on reducing emissions and operating costs, there is a need for efficient and …

Multimodal Neuron Classification Based On Morphology And Electrophysiology, Aqib Ahmad

Graduate Theses, Dissertations, and Problem Reports

Categorizing neurons into different types to understand neural circuits and ultimately brain function is a major challenge in neuroscience. While electrical properties are critical in defining a neuron, its morphology is equally important. Advancements in single-cell analysis methods have allowed neuroscientists to simultaneously capture multiple data modalities from a neuron. We propose a method to classify neurons using both morphological structure and electrophysiology. Current approaches are based on a limited analysis of morphological features. We propose to use a new graph neural network to learn representations that more comprehensively account for the complexity of the shape of neuronal structures. In …

Sequence Checking And Deduplication For Existing Fingerprint Databases, Tahsin Islam Sakif

Graduate Theses, Dissertations, and Problem Reports

Biometric technology is a rapidly evolving field with applications that range from access to devices to border crossing and entry/exit processes. Large-scale applications to collect biometric data, such as border crossings result in multimodal biometric databases containing thousands of identities. However, due to human operator error, these databases often contain many instances of image labeling and classification; this is due to the lack of training and throughput pressure that comes with human error. Multiple entries from the same individual may be assigned to a different identity. Rolled fingerprints may be labeled as flat images, a face image entered into a …

Exploiting The Advantages And Overcoming The Challenges Of The Cable In A Tethered Drone System, Rogerio Rodrigues Lima

Graduate Theses, Dissertations, and Problem Reports

This dissertation proposes solutions for motion planning, localization, and landing of tethered drones using only tether variables. A tether-based multi-model localization framework for tethered drones is proposed. This framework comprises three independent localization strategies based on a different model. The first strategy uses simple trigonometric relations assuming that the tether is taut; the second method relies on a set of catenary equations for the slack tether case; the third estimator is a neural network-based predictor that can cover different tether shapes. Multi-layer perceptron networks previously trained with a dataset comprised of the tether variables (i.e., length, tether angles on the …

Generative Prior For Unsupervised Image Restoration, Ahmed Cheikh Sidiya

Graduate Theses, Dissertations, and Problem Reports

The challenge of restoring real world low-quality images is due to a lack of appropriate training data and difficulty in determining how the image was degraded. Recently, generative models have demonstrated great potential for creating high- quality images by utilizing the rich and diverse information contained within the model’s trained weights and learned latent representations. One popular type of generative model is the generative adversarial network (GAN). Many new methods have been developed to harness the information found in GANs for image manipulation. Our proposed approach is to utilize generative models for both understanding the degradation of an image and …

Knowledge Discovery On The Integrative Analysis Of Electrical And Mechanical Dyssynchrony To Improve Cardiac Resynchronization Therapy, Zhuo He

Dissertations, Master's Theses and Master's Reports

Cardiac resynchronization therapy (CRT) is a standard method of treating heart failure by coordinating the function of the left and right ventricles. However, up to 40% of CRT recipients do not experience clinical symptoms or cardiac function improvements. The main reasons for CRT non-response include: (1) suboptimal patient selection based on electrical dyssynchrony measured by electrocardiogram (ECG) in current guidelines; (2) mechanical dyssynchrony has been shown to be effective but has not been fully explored; and (3) inappropriate placement of the CRT left ventricular (LV) lead in a significant number of patients.

In terms of mechanical dyssynchrony, we utilize an …

Exploring Different Mediums For Teaching Programming And Cybersecurity In Primary And Secondary Schools, Andrew R. Youngstrom

Dissertations, Master's Theses and Master's Reports

Cybersecurity and programming are becoming more and more prominent in today’s world. It is beneficial to begin teaching these topics to students at a younger age. Additionally, we see students in primary and secondary schools struggling to maintain focus in class as attention spans shrink. This paper looks at different drone models to see if any of them could be sufficient solutions to be implemented into primary and secondary schools to teach cybersecurity and programming topics to students. Besides teaching capabilities, drones must also be affordable for institutions and simple enough to construct, configure, and operate so that a teacher …

Chatgpt In Higher Education: Considerations For Academic Integrity And Student Learning, Miriam Sullivan, Andrew Kelly, Paul Mclaughlan

Research outputs 2022 to 2026

The release of ChatGPT has sparked significant academic integrity concerns in higher education. However, some commentators have pointed out that generative artificial intelligence (AI) tools such as ChatGPT can enhance student learning, and consequently, academics should adapt their teaching and assessment practices to embrace the new reality of living, working, and studying in a world where AI is freely available. Despite this important debate, there has been very little academic literature published on ChatGPT and other generative AI tools. This article uses content analysis to examine news articles (N=100) about how ChatGPT is disrupting higher education, concentrating specifically on Australia, …

Automated Short-Answer Grading And Misconception Detection Using Large Language Models, Nazmul H. Kazi

UNF Graduate Theses and Dissertations

As education technology continues to evolve, the domains of Automatic Short-Answer Grading (ASAG) and Automated Misconception Detection (AMD) stand at the forefront of innovative approaches to educational assessment. We explore the transformative potential of Large Language Models (LLMs) in revolutionizing these critical areas. Leveraging the remarkable capabilities of LLMs in semantic inference, contextual understanding, and transfer learning, we embark on a comprehensive journey to enhance both ASAG and AMD. On ASAG, we illuminate the efficacy of transfer learning by fine-tuning RoBERTa Large, a state-of-the-art LLM, on task-related corpora, e.g. the Multi-Genre Natural Language Inference (MNLI) corpus. The model's adaptability across …

Multi-Domain Adaptation For Image Classification, Depth Estimation, And Semantic Segmentation, Yu Zhang

Theses and Dissertations--Computer Science

The appearance of scenes may change for many reasons, including the viewpoint, the time of day, the weather, and the seasons. Traditionally, deep neural networks are trained and evaluated using images from the same scene and domain to avoid the domain gap. Recent advances in domain adaptation have led to a new type of method that bridges such domain gaps and learns from multiple domains.

This dissertation proposes methods for multi-domain adaptation for various computer vision tasks, including image classification, depth estimation, and semantic segmentation. The first work focuses on semi-supervised domain adaptation. I address this semi-supervised setting and propose …

How Ai Can Learn From The Law: Putting Humans In The Loop Only On Appeal, I. Glenn Cohen, Boris Babic, Sara Gerke, Qiong Xia,, Theodoros Evgeniou, Klaus Wertenbroch

Faculty Scholarly Works

While the literature on putting a “human in the loop” in artificial intelligence (AI) and machine learning (ML) has grown significantly, limited attention has been paid to how human expertise ought to be combined with AI/ML judgments. This design question arises because of the ubiquity and quantity of algorithmic decisions being made today in the face of widespread public reluctance to forgo human expert judgment. To resolve this conflict, we propose that human expert judges be included via appeals processes for review of algorithmic decisions. Thus, the human intervenes only in a limited number of cases and only after an …

Object Detection And Image Categorization By Transferring Commonsense Knowledge With Premises And Quantifiers, Irina Chernyavsky

Theses, Dissertations and Culminating Projects

Domestic, or household robots, are autonomous robots designed to make our home-life easier by performing chores and mundane tasks such as cleaning, or cooking. Currently domestic robots are specialized to complete a specific task and, therefore, are confined by factors such as mobility, size, and complexity. With the fast development of computer vision and robotics, the need for more compact, advanced and multi-task robots has emerged. Therefore, the robot needs to be multi-functional, able to discern the environment and the tasks. The aim of this paper is to categorize images in domestic robots as relevant to the culinary, laundry, vacuum …

Aspect Sentiment Triplet Extraction Incorporating Syntactic Constituency Parsing Tree And Commonsense Knowledge Graph, Zhenda Hu, Zhaoxia Wang, Yinglin Wang, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

The aspect sentiment triplet extraction (ASTE) task aims to extract the target term and the opinion term, and simultaneously identify the sentiment polarity of target-opinion pairs from the given sentences. While syntactic constituency information and commonsense knowledge are both important and valuable for the ASTE task, only a few studies have explored how to integrate them via flexible graph convolutional networks (GCNs) for this task. To address this gap, this paper proposes a novel end-to-end model, namely GCN-EGTS, which is an enhanced Grid Tagging Scheme (GTS) for ASTE leveraging syntactic constituency parsing tree and a commonsense knowledge graph based on …

Seven Pillars For The Future Of Artificial Intelligence, Erik Cambria, Rui Mao, Melvin Chen, Zhaoxia Wang, Seng-Beng Ho

Research Collection School Of Computing and Information Systems

In recent years, AI research has showcased tremendous potential to impact positively humanity and society. Although AI frequently outperforms humans in tasks related to classification and pattern recognition, it continues to face challenges when dealing with complex tasks such as intuitive decision-making, sense disambiguation, sarcasm detection, and narrative understanding, as these require advanced kinds of reasoning, e.g., commonsense reasoning and causal reasoning, which have not been emulated satisfactorily yet. To address these shortcomings, we propose seven pillars that we believe represent the key hallmark features for the future of AI, namely: Multidisciplinarity, Task Decomposition, Parallel Analogy, Symbol Grounding, Similarity Measure, …

Automatic Scoring Of Speeded Interpersonal Assessment Center Exercises Via Machine Learning: Initial Psychometric Evidence And Practical Guidelines, Louis Hickman, Christoph N. Herde, Filip Lievens, Louis Tay

Research Collection Lee Kong Chian School Of Business

Assessment center (AC) exercises such as role-plays have established themselves as valuable approaches for obtaining insights into interpersonal behavior, but they are often considered the “Rolls Royce” of personnel assessment due to their high costs. The observation and rating process comprises a substantial part of these costs. In an exploratory case study, we capitalize on recent advances in natural language processing (NLP) by developing NLP-based machine learning (ML) models to investigate the possibility of automatically scoring AC exercises. First, we compared the convergent-related validity and contamination with word count of ML scores based on models that used different NLP methods …

Fast Multiscale Functional Estimation In Optimal Emg Placement For Robotic Prosthesis Controllers, Jin Ren, Guohui Song, Lucia Tabacu, Yuesheng Xu

Mathematics & Statistics Faculty Publications

Electromyogram (EMG) signals play a significant role in decoding muscle contraction information for robotic hand prosthesis controllers. Widely applied decoders require a large amount of EMG signals sensors, resulting in complicated calculations and unsatisfactory predictions. By the biomechanical process of single degree-of-freedom human hand movements, only several EMG signals are essential for accurate predictions. Recently, a novel predictor of hand movements adopted a multistage sequential adaptive functional estimation (SAFE) method based on the historical functional linear model (FLM) to select important EMG signals and provide precise projections.

However, SAFE repeatedly performs matrix-vector multiplications with a dense representation matrix of the …

Understanding Human-Centred Artificial Intelligence In The Banking Sector, Krishnaraj Arul Obuchettiar, Alan @ Ali Madjelisi Megargel

Research Collection Lee Kong Chian School Of Business

The advent of smart digital devices and social media has shaped how consumers interact and transact with their financial institutions. Consumers increasingly want hyperpersonalised interactions that are more frequent and proactive, while financial institutions have a growing need to cater to consumers’ new demands. Financial institutions, such as banks, continuously adapt to the latest technologies to keep pace with evolving customer behaviours, needs, and experiences. One such emerging technology is artificial intelligence (AI). Many organisations realise the potential of AI; however, a human-centred AI system must be capable of understanding human characteristics and making decisions like humans. This paper presents …

Deep Learning-Based Technique For The Perception Of The Cervical Cancer, Aya Haraz, Hossam El-Din Moustafa, Abeer Twakol Khaleel, Ahmed H. Eltanboly

Mansoura Engineering Journal

In third-world countries, cervical cancer is the most prevalent and leading cause of death. It is affected by a variety of factors, including smoking, poor nutritional status, immunological inadequacy, and prolonged use of contraception. The Pap smear test, which is intended to prevent cervical cancer, finds preneoplastic changes in cervical epithelial cells. This study framework classified cervical cancer cells from Pap smears into five specified cell types using machine learning-based classification algorithms. The SIPaKMeD database is used in this investigation. This public dataset, which was manually cropped from 966 cluster cell images taken from Pap smear slides, has 4045 isolated …

Machine Learning Framework For Real-World Electronic Health Records Regarding Missingness, Interpretability, And Fairness, Jing Lucas Liu

Theses and Dissertations--Computer Science

Machine learning (ML) and deep learning (DL) techniques have shown promising results in healthcare applications using Electronic Health Records (EHRs) data. However, their adoption in real-world healthcare settings is hindered by three major challenges. Firstly, real-world EHR data typically contains numerous missing values. Secondly, traditional ML/DL models are typically considered black-boxes, whereas interpretability is required for real-world healthcare applications. Finally, differences in data distributions may lead to unfairness and performance disparities, particularly in subpopulations.

This dissertation proposes methods to address missing data, interpretability, and fairness issues. The first work proposes an ensemble prediction framework for EHR data with large missing …

The Basil Technique: Bias Adaptive Statistical Inference Learning Agents For Learning From Human Feedback, Jonathan Indigo Watson

Theses and Dissertations--Computer Science

We introduce a novel approach for learning behaviors using human-provided feedback that is subject to systematic bias. Our method, known as BASIL, models the feedback signal as a combination of a heuristic evaluation of an action's utility and a probabilistically-drawn bias value, characterized by unknown parameters. We present both the general framework for our technique and specific algorithms for biases drawn from a normal distribution. We evaluate our approach across various environments and tasks, comparing it to interactive and non-interactive machine learning methods, including deep learning techniques, using human trainers and a synthetic oracle with feedback distorted to varying degrees. …

Symbolic Computation Of Squared Amplitudes In High Energy Physics With Machine Learning, Abdulhakim Alnuqaydan

Theses and Dissertations--Physics and Astronomy

The calculation of particle interaction squared amplitudes is a key step in the calculation of cross sections in high-energy physics. These complex calculations are currently performed using domain-specific symbolic algebra tools, where the computational time escalates rapidly with an increase in the number of loops and final state particles. This dissertation introduces an innovative approach: employing a transformer-based sequence-to-sequence model capable of accurately predicting squared amplitudes of Standard Model processes up to one-loop order when trained on symbolic sequence pairs. The primary objective of this work is to significantly reduce the computational time and, more importantly, develop a model that …

Is Disclosure And Certification Of The Use Of Generative Ai Really Necessary?, Maura R. Grossman, Paul W. Grimm, Daniel G. Brown

Faculty Scholarship

No abstract provided.