Computer Sciences Commons^™

Research And Development Of Immersive Aero-Engine Scene Simulation System, Shun Yao, Zhongzhi Hu, Wenyu Cao, Jiali Yang

Journal of System Simulation

The research and development of aero-engines has the characteristics of high precision and interdiscipline. In order to reduce communication costs and to display the engine structure and the state of semi-physical simulator, by applying virtual reality technology,an immersive scene simulation system is built. By studying CAD data lightweight technology and physics-based real-time rendering technology,a rendering optimization method for similar object dynamic batching is proposed, which effectively improves the rendering frame rate. A dynamic parallax adjustment algorithm is proposed to solve the problem of dizziness when having a close look to stereoscopic images. The system achieves the …

Fine-Tuned Clip Models Are Efficient Video Learners, Hanoona Rasheed, Muhammad Uzair Khattak, Muhammad Maaz, Salman Khan, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the video domain. In this pursuit, new parametric modules are added to learn temporal information and inter-frame relationships which require meticulous design efforts. Furthermore, when the resulting models are learned on videos, they tend to overfit on the given task distribution and lack in generalization aspect. This begs the following question: How to effectively transfer image-level CLIP representations to videos? In this work, we show that a …

Person Image Synthesis Via Denoising Diffusion Model, Ankan Kumar Bhunia, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Jorma Laaksonen, Mubarak Shah, Fahad Shahbaz Khan

Computer Vision Faculty Publications

The pose-guided person image generation task requires synthesizing photorealistic images of humans in arbitrary poses. The existing approaches use generative adversarial networks that do not necessarily maintain realistic textures or need dense correspondences that struggle to handle complex deformations and severe occlusions. In this work, we show how denoising diffusion models can be applied for high-fidelity person image synthesis with strong sample diversity and enhanced mode coverage of the learnt data distribution. Our proposed Person Image Diffusion Model (PIDM) disintegrates the complex transfer problem into a series of simpler forward-backward denoising steps. This helps in learning plausible source-to-target transformation trajectories …

Attention Visual, Baris Dingil

College of Computing and Digital Media Dissertations

This research presents an innovative approach to improving visual-spatial attention using a research tool based on the web. Recognizing the significant role visual-spatial attention plays in everyday life and cognitive function for humans, this research was undertaken with the aim of developing a user-friendly, accessible web-based tool called Attention Visual (attentionvisual.com) to enhance this crucial cognitive skill. This tool also facilitates data collection, potentially accelerating the pace and enhancing the quality of related research. Both qualitative and quantitative methods were utilized for data collection and analysis. In order to stimulate improvements in visual-spatial attention, the tool’s algorithm was structured to …

Digital Twin Haptic Robotic Arms: Towards Handshakes In The Metaverse, Mohd Faisal, Fedwa Laamarti, Abdulmotaleb El Saddik

Computer Vision Faculty Publications

More daily interactions are happening in the digital world of the metaverse. Providing individuals with means to perform a handshake during these interactions can enhance the overall user experience. In this paper, we put forward the design and implementation of two right-handed underactuated Digital Twin robotic arms to mediate the physical handshake interaction between two individuals. This allows them to perform a handshake while they are in separate locations. The experimental findings are very promising as our evaluation shows that the participants were highly interested in using our system to shake hands with their loved ones when they are physically …

Utilizing Few-Shot Meta Learning Algorithms For Medical Image Segmentation, Nick Littlefield

Thinking Matters Symposium

Deep learning models can be difficult to train because they require large amounts of data, which we usually do not have or are too expensive to get or annotate. To overcome this problem, we can use few-shot meta-learning, which allows us to train deep learning models with little data. Using a few examples, meta-learning, or learning-to-learn, aims to use the experience learned during training to generalize to unknown tasks. Medical imaging is an industry where it is particularly useful, as there is limited publicly available data due to patient privacy concerns and annotating costs.

This project examines how meta-learning performs …

Joint Flood Risks In The Grand River Watershed, Poornima Unnikrishnan, Kumaraswamy Ponnambalam, Nirupama Agrawal, Fakhri Karray

Machine Learning Faculty Publications

According to the World Meteorological Organization, since 2000, there has been an increase in global flood-related disasters by 134 percent compared to the previous decades. Efficient flood risk management strategies necessitate a holistic approach to evaluating flood vulnerabilities and risks. Catastrophic losses can occur when the peak flow values in the rivers in a basin coincide. Therefore, estimating the joint flood risks in a region is vital, especially when frequent occurrences of extreme events are experienced. This study focuses on estimating the joint flood risks due to river flow extremes in the Grand River watershed in Canada. For this purpose, …

Adversary Aware Continual Learning, Muhammad Umer

Theses and Dissertations

Continual learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, these approaches are adversary agnostic, i.e., they do not consider the possibility of malicious attacks. In this dissertation, we have demonstrated that continual learning approaches are extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can introduce small amount of misinformation to the model in the form of imperceptible backdoor pattern during training to cause deliberate forgetting of a specific class at test time. We then propose a novel defensive framework to counter …

Machine Learning Data Feature Reduction And Model Optimization, Francisco P. Maturana, Phillip M. Lacasse

AFIT Patents

For machine learning data reduction and model optimization, a method randomly assigns each data feature of a training data set to a plurality of solution groups. Each solution group has no more than a solution group number k of data features and each data feature is assigned to a plurality of solution groups. The method identifies each solution group as a high-quality solution group or a low-quality solution group. The method further calculates data feature scores for each data feature comprising a high bin number and a low bin number. The method determines level data for each data feature from …

Towards An Experimental Bibliography Of Hemispheric Reconstruction Newspapers, Joshua Ortiz Baco, Benjamin Charles Germain Lee, Jim Casey, Sarah H. Salter

Criticism

Digital collections of newspapers have drawn broader attention to the fragmented and scattered print histories of minoritized communities. Attempts to survey these histories through bibliography, however, quickly meet with a fundamental problem: the practice of bibliographic description calls for creating a static record of social affiliations. Given the overwhelming scholarly consensus that categories such as race, ethnicity, and language are socially constructed, this article introduces an experimental bibliographic method for mapping the vast landscape of historical newspapers. This method extends the machine learning affordances of a recent project called Newspaper Navigator to enumerate the newspapers in Chronicling America according to …

Poly-Gan: Regularizing Polygons With Generative Adversarial Networks, Lasith Niroshan, James Carswell

Conference Papers

Regularizing polygons involves simplifying irregular and noisy shapes of built environment objects (e.g. buildings) to ensure that they are accurately represented using a minimum number of vertices. It is a vital processing step when creating/transmitting online digital maps so that they occupy minimal storage space and bandwidth. This paper presents a data-driven and Deep Learning (DL) based approach for regularizing OpenStreetMap building polygon edges. The study introduces a building footprint regularization technique (Poly-GAN) that utilises a Generative Adversarial Network model trained on irregular building footprints and OSM vector data. The proposed method is particularly relevant for map features …

Stereotypes And Language Models: Understanding How Language Models Encode Stereotypes, Debiasing Language Models, And Examining How Stereotypes Affect Conversations, Brian C. Wang

Computer Science Senior Theses

This thesis describes a variety of approaches in examining how language models encode stereotypes (understanding stereotypes from a model point-of-view), debiasing language models, and using language models to understand how stereotypes affect conversations (understanding stereotypes from a conversational point-of-view). We present a novel approach for textual clues analysis that makes language models more interpretable, combining the understanding of what stereotypes the internal structures of language models have encoded during their initial training (via attention-based analysis) and understanding what textual clues are most relevant to identifying stereotypes for models trained to detect stereotypes (via SHAP-based analysis). We find that different pre-trained …

Sarcasm Detection In English And Arabic Tweets Using Transformer Models, Rishik Lad

Computer Science Senior Theses

This thesis describes our approach toward the detection of sarcasm and its various types in English and Arabic Tweets through methods in deep learning. There are five problems we attempted: (1) detection of sarcasm in English Tweets, (2) detection of sarcasm in Arabic Tweets, (3) determining the type of sarcastic speech subcategory for English Tweets, (4) determining which of two semantically equivalent English Tweets is sarcastic, and (5) determining which of two semantically equivalent Arabic Tweets is sarcastic. All tasks were framed as classification problems, and our contributions are threefold: (a) we developed an English binary classifier system with RoBERTa, …

Ai Art: Artists’ Best Friend Or Mortal Enemy?, Ethan Gabrys

Tredway Library Prize for First-Year Research

This paper analyzes the impacts and implications of generative AI software on art and examines the ethics of using such tools. Through the argument that careless use of these tools presents a danger to the art world as they risk devaluing human expression, Gabrys states that “as what it means to be human changes with each generation, new artists express sentiment through their art. Art has the ability to tell us about the human experience.” He concludes that the use of AI tools takes the skill and sentiment of human artists out of the equation, begging the question: if the …

Suitability Of Sdn And Mec To Facilitate Digital Twin Communication Over Lte-A, Hikmat Adhami, Mohammad Alja'afreh, Mohamed Hoda, Jiaqi Zhao, Yong Zhou, Abdulmotaleb Elsaddik

Computer Vision Faculty Publications

Haptic is the modality that complements traditional multimedia, i.e., audiovisual, to evolve the next wave of innovation at which the Internet data stream can be exchanged to enable remote skills and control applications. This will require ultra-low latency and ultra-high reliability to evolve the mobile experience into the era of Digital Twin and Tactile Internet. While the 5th generation of mobile networks is not yet widely deployed, Long-Term Evolution (LTE-A) latency remains much higher than the 1 ms requirement for the Tactile Internet and therefore the Digital Twin. This work investigates an interesting solution based on the incorporation of Software-defined …

An Investigation Into Machine Learning Techniques For Designing Dynamic Difficulty Agents In Real-Time Games, Ryan Adare Dunagan

Electronic Theses and Dissertations

Video games are an incredibly popular pastime enjoyed by people of all ages world wide. Many different kinds of games exist, but most games feature some elements of the player overcoming some challenge, usually through gameplay. These challenges are insurmountable for some people and may turn them off to video games as a pastime. Games can be made more accessible to players of little skill and/or experience through the use of Dynamic Difficulty Adjustment (DDA) systems that adjust the difficulty of the game in response to the player’s performance. This research seeks to establish the effectiveness of machine learning techniques …

Human-Ai Collaboration For Smart Education: Reframing Applied Learning To Support Metacognition, James Hutson, Daniel Plate

Faculty Scholarship

This chapter investigates the profound influence of intelligent virtual assistants (IVAs) on the educational domain, specifically in the realm of individualized learning and the instruction of writing abilities and content creation. IVAs, incorporating generative AI technologies such as ChatGPT and Stable Diffusion, hold the potential to bring about a paradigm shift in educational programs, emphasizing the enhancement of advanced metacognitive capacities rather than the fundamentals of communication. The subsequent recommendations stress the need to cultivate enduring proficiencies and ascertain tailored learning approaches for each learner, which will be indispensable for success in the evolving job market. In this context, prompt …

Exploring The Educational Potential Of Ai Generative Art In 3d Design Fundamentals: A Case Study On Prompt Engineering And Creative Workflows, James Hutson, Bryan Robertson

Faculty Scholarship

AI will be increasingly integrated into artistic practices and creative workflows with prompt engineering assuming an increasingly important role in the process. With readilyavailable generative AI, such as Midjourney, DALL-E 2, and Craiyon (formerly DALLE-mini), anyone can seemingly create "art,” prompting questions about the future necessity of art and design education. However, whereas the ease with which content can be created has seen an outcry from the traditional artmaking community, fears over widespread adoption replacing the need for a firm foundation in art and design principles and fundamentals is unfounded. Instead, these tools should be seen and adopted as other …

Predicting Location And Training Effectiveness (Plate), Erik Rolf Bruenner

Master's Theses

Abstract Predicting Location and Training Effectiveness (PLATE)
Erik Bruenner

Physical activity and exercise have been shown to have an enormous impact on many areas of human health and can reduce the risk of many chronic diseases. In order to better understand how exercise may affect the body, current kinesiology studies are designed to track human movements over large intervals of time. Procedures used in these studies provide a way for researchers to quantify an individual’s activity level over time, along with tracking various types of activities that individuals may engage in. Movement data of research subjects is often collected through …

---

Go to article

Neural Tabula Rasa: Foundations For Realistic Memories And Learning, Patrick R. Perrine

Master's Theses

Understanding how neural systems perform memorization and inductive learning tasks are of key interest in the field of computational neuroscience. Similarly, inductive learning tasks are the focus within the field of machine learning, which has seen rapid growth and innovation utilizing feedforward neural networks. However, there have also been concerns regarding the precipitous nature of such efforts, specifically in the area of deep learning. As a result, we revisit the foundation of the artificial neural network to better incorporate current knowledge of the brain from computational neuroscience. More specifically, a random graph was chosen to model a neural system. This …

Structural Anomaly Detection, Shoufu Luo

Dissertations, Theses, and Capstone Projects

As computer systems become more complex and powerful, the threat of sophisticated and persistent computer attacks increases dramatically. Traditional intrusion detection systems that rely on log analysis struggle to keep pace with these evolving threats, as the attacking trails are often buried in high-volume and high-velocity legitimate activities in the system. Despite tremendous progress in applying machine learning techniques to anomaly-based intrusion detection, such methods continue to suffer from a high false positive rate due to the diversity and variability of individual behavior.To address this problem, this thesis proposes a new framework for detecting structural anomalies in computer systems. The …

Evaluating Neural Networks As Cognitive Models For Learning Quasi-Regularities In Language, Xiaomeng Ma

Dissertations, Theses, and Capstone Projects

Many aspects of language can be categorized as quasi-regular: the relationship between the inputs and outputs is systematic but allows many exceptions. Common domains that contain quasi-regularity include morphological inflection and grapheme-phoneme mapping. How humans process quasi-regularity has been debated for decades. This thesis implemented modern neural network models, transformer models, on two tasks: English past tense inflection and Chinese character naming, to investigate how transformer models perform quasi-regularity tasks. This thesis focuses on investigating to what extent the models' performances can represent human behavior. The results show that the transformers' performance is very similar to human behavior in many …

Patient Movement Monitoring Based On Imu And Deep Learning, Mohsen Sharifi Renani

Electronic Theses and Dissertations

Osteoarthritis (OA) is the leading cause of disability among the aging population in the United States and is frequently treated by replacing deteriorated joints with metal and plastic components. Developing better quantitative measures of movement quality to track patients longitudinally in their own homes would enable personalized treatment plans and hasten the advancement of promising new interventions. Wearable sensors and machine learning used to quantify patient movement could revolutionize the diagnosis and treatment of movement disorders. The purpose of this dissertation was to overcome technical challenges associated with the use of wearable sensors, specifically Inertial Measurement Units (IMUs), as a …

Imitating Opponent To Win: Adversarial Policy Imitation Learning In Two-Player Competitive Games, The Viet Bui, Tien Mai, Thanh H. Nguyen

Research Collection School Of Computing and Information Systems

Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In existing studies, adversarial policies are directly trained based on experiences of interacting with the victim agent. There is a key shortcoming of this approach --- knowledge derived from historical interactions may not be properly generalized to unexplored policy regions of the victim agent, making the trained adversarial policy significantly less effective. In this work, we design a new effective adversarial policy learning algorithm that overcomes …

Venus: A Geometrical Representation For Quantum State Visualization, Shaolun Ruan, Ribo Yuan, Qiang Guan, Yanna Lin, Ying Mao, Weiwen Jiang, Zhepeng Wang, Wei Xu, Yong Wang

Research Collection School Of Computing and Information Systems

Visualizations have played a crucial role in helping quantum computing users explore quantum states in various quantum computing applications. Among them, Bloch Sphere is the widely-used visualization for showing quantum states, which leverages angles to represent quantum amplitudes. However, it cannot support the visualization of quantum entanglement and superposition, the two essential properties of quantum computing. To address this issue, we propose VENUS, a novel visualization for quantum state representation. By explicitly correlating 2D geometric shapes based on the math foundation of quantum computing characteristics, VENUS effectively represents quantum amplitudes of both the single qubit and two qubits for quantum …

Where Is My Spot? Few-Shot Image Generation Via Latent Subspace Optimization, Chenxi Zheng, Bangzhen Liu, Huaidong Zhang, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Image generation relies on massive training data that can hardly produce diverse images of an unseen category according to a few examples. In this paper, we address this dilemma by projecting sparse few-shot samples into a continuous latent space that can potentially generate infinite unseen samples. The rationale behind is that we aim to locate a centroid latent position in a conditional StyleGAN, where the corresponding output image on that centroid can maximize the similarity with the given samples. Although the given samples are unseen for the conditional StyleGAN, we assume the neighboring latent subspace around the centroid belongs to …

Generative Ai Tools In Art Education: Exploring Prompt Engineering And Iterative Processes For Enhanced Creativity, James Hutson, Peter Cotroneo

Faculty Scholarship

The rapid development and adoption of generative artificial intelligence (AI) tools in the art and design education landscape have introduced both opportunities and challenges. This timely study addresses the need to effectively integrate these tools into the classroom while considering ethical implications and the importance of prompt engineering. By examining the iterative process of refining original ideas through multiple iterations, verbal expansion, and the use of OpenAI’s DALL E2 for generating diverse visual outcomes, researchers gain insights into the potential benefits and pitfalls of these tools in an educational context. Students in the digital at case study were taught prompt …

A Novel Approach To Extending Music Using Latent Diffusion, Keon Roohparvar, Franz J. Kurfess

Master's Theses

Using deep learning to synthetically generate music is a research domain that has gained more attention from the public in the past few years. A subproblem of music generation is music extension, or the task of taking existing music and extending it. This work proposes the Continuer Pipeline, a novel technique that uses deep learning to take music and extend it in 5 second increments. It does this by treating the musical generation process as an image generation problem; we utilize latent diffusion models (LDMs) to generate spectrograms, which are image representations of music. The Continuer Pipeline is able to …

Life, Death, And Ai: Exploring Digital Necromancy In Popular Culture—Ethical Considerations, Technological Limitations, And The Pet Cemetery Conundrum, James Hutson, Jay Ratican

Faculty Scholarship

This article explores the rise of generative AI, particularly ChatGPT, and the combination of large language models (LLM) with robotics, exemplified by Ameca the Robot. It addresses the need to study the ethical considerations and potential implications of digital necromancy, which involves using AI to reanimate deceased individuals for various purposes. Reasons for desiring to engage with a disembodied or bodied replica of a person include the preservation of memories, emotional closure, cultural heritage and historical preservation, interacting with idols or influential figures, educational and research purposes, and creative expression and artistic endeavors. As such, this article examines historical examples …

Tree-Based Unidirectional Neural Networks For Low-Power Computer Vision, Abhinav Goel, Caleb Tung, Nick Eliopoulos, Amy Wang, Jamie C. Davis, George K. Thiruvathukal, Yung-Hisang Lu

Computer Science: Faculty Publications and Other Works

This article describes the novel Tree-based Unidirectional Neural Network (TRUNK) architecture. This architecture improves computer vision efficiency by using a hierarchy of multiple shallow Convolutional Neural Networks (CNNs), instead of a single very deep CNN. We demonstrate this architecture’s versatility in performing different computer vision tasks efficiently on embedded devices. Across various computer vision tasks, the TRUNK architecture consumes 65% less energy and requires 50% less memory than representative low-power CNN architectures, e.g., MobileNet v2, when deployed on the NVIDIA Jetson Nano.