Physical Sciences and Mathematics Commons^™

Feature Prediction Diffusion Model For Video Anomaly Detection, Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang

Research Collection School Of Computing and Information Systems

Anomaly detection in the video is an important research area and a challenging task in real applications. Due to the unavailability of large-scale annotated anomaly events, most existing video anomaly detection (VAD) methods focus on learning the distribution of normal samples to detect the substantially deviated samples as anomalies. To well learn the distribution of normal motion and appearance, many auxiliary networks are employed to extract foreground object or action information. These high-level semantic features effectively filter the noise from the background to decrease its influence on detection models. However, the capability of these extra semantic models heavily affects the …

Hallucination Detection: Robustly Discerning Reliable Answers In Large Language Models, Yuyuan Chen, Qiang Fu, Yichen Yuan, Zhihao Wen, Ge Fan, Dayiheng Liu, Dongmei Zhang, Zhixu Li, Yanghua Xiao

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems. However, a major drawback of LLMs is the issue of hallucination, where they generate unfaithful or inconsistent content that deviates from the input source, leading to severe consequences. In this paper, we propose a robust discriminator named RelD to effectively detect hallucination in LLMs' generated answers. RelD is trained on the constructed RelQA, a bilingual question-answering dialogue dataset along with answers generated by LLMs and a comprehensive set of metrics. Our experimental results demonstrate that the proposed RelD successfully detects …

Unsupervised Anomaly Detection In Medical Images With A Memory-Augmented Multi-Level Cross-Attentional Masked Autoencoder, Yu Tian, Guansong Pang, Yuyuan Liu, Chong Wang, Yuanhong Chen, Fengbei Liu, Rajvinder Singh, Johan W. Verjans, Mengyu Wang, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection (UAD) aims to find anomalous images by optimising a detector using a training set that contains only normal images. UAD approaches can be based on reconstruction methods, self-supervised approaches, and Imagenet pre-trained models. Reconstruction methods, which detect anomalies from image reconstruction errors, are advantageous because they do not rely on the design of problem-specific pretext tasks needed by self-supervised approaches, and on the unreliable translation of models pre-trained from non-medical datasets. However, reconstruction methods may fail because they can have low reconstruction errors even for anomalous images. In this paper, we introduce a new reconstruction-based UAD approach …

Application And Use Of Artificial Intelligence (Ai) For Library Services Delivery In Academic Libraries In Kwara State, Nigeria, Abdullahi Olayinka Isiaka

Library Philosophy and Practice (e-journal)

The application and use Artificial Intelligence (AI) in library services delivery and operations has modernized traditional practices, enabling libraries to adapt to the evolving information needs of patrons in the digital era. The main purpose of this study is to investigate the application and use of Artificial Intelligence (AI) Technologies for Library Services Delivery in Academic Libraries in Kwara State, Nigeria. The study used a descriptive survey approach. The population was the 108 librarians in academic libraries in Kwara State, Nigeria. A total enumeration technique was employed, and a questionnaire was used to collect data from the library staff. The …

Online Aircraft System Identification Using A Novel Parameter Informed Reinforcement Learning Method, Nathan Schaff

Doctoral Dissertations and Master's Theses

This thesis presents the development and analysis of a novel method for training reinforcement learning neural networks for online aircraft system identification of multiple similar linear systems, such as all fixed wing aircraft. This approach, termed Parameter Informed Reinforcement Learning (PIRL), dictates that reinforcement learning neural networks should be trained using input and output trajectory/history data as is convention; however, the PIRL method also includes any known and relevant aircraft parameters, such as airspeed, altitude, center of gravity location and/or others. Through this, the PIRL Agent is better suited to identify novel/test-set aircraft.

First, the PIRL method is applied to …

Dexbert: Effective, Task-Agnostic And Fine-Grained Representation Learning Of Android Bytecode, Tiezhu Sun, Kevin Allix, Kisub Kim, Xin Zhou, Dongsun Kim, David Lo, Tegawendé F. Bissyande, Jacques Klein

Research Collection School Of Computing and Information Systems

The automation of an increasingly large number of software engineering tasks is becoming possible thanks to Machine Learning (ML). One foundational building block in the application of ML to software artifacts is the representation of these artifacts ( e.g. , source code or executable code) into a form that is suitable for learning. Traditionally, researchers and practitioners have relied on manually selected features, based on expert knowledge, for the task at hand. Such knowledge is sometimes imprecise and generally incomplete. To overcome this limitation, many studies have leveraged representation learning, delegating to ML itself the job of automatically devising suitable …

Intelligence Versus Inferno: How Artificial Intelligence Can Be Used To Monitor And Manage Wildfires In Europe, Maxwell Feldman

Independent Study Project (ISP) Collection

Escalating wildfire occurrences in Europe, particularly in the southern Mediterranean region, are presenting significant challenges to socioeconomic, environmental, and ecosystem services. The increasing frequency and severity of these wildfires are straining resources and emphasizing the need for a better understanding of the relationship between suppression capacity and fire behavior in wildfire management. The following research addresses the urgent need for more proactive, knowledge-based, and technologically driven fire management strategies, throughout all four stages of wildfire response – fuel and land management, fire preparedness, fire suppression, and post-fire management. Artificial Intelligence (AI) is becoming increasingly significant in climate change adaptation, especially …

Spoken Language Processing And Modeling For Aviation Communications, Aaron Van De Brook

Doctoral Dissertations and Master's Theses

With recent advances in machine learning and deep learning technologies and the creation of larger aviation-specific corpora, applying natural language processing technologies, especially those based on transformer neural networks, to aviation communications is becoming increasingly feasible. Previous work has focused on machine learning applications to natural language processing, such as N-grams and word lattices. This thesis experiments with a process for pretraining transformer-based language models on aviation English corpora and compare the effectiveness and performance of language models transfer learned from pretrained checkpoints and those trained from their base weight initializations (trained from scratch). The results suggest that transformer language …

Deep Reinforcement Learning With Explicit Context Representation, Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji

Research Collection School Of Computing and Information Systems

Though reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems, most RL algorithms lack an explicit method that would allow learning from contextual information. On the other hand, humans often use context to identify patterns and relations among elements in the environment, along with how to avoid making wrong actions. However, what may seem like an obviously wrong decision from a human perspective could take hundreds of steps for an RL agent to learn to avoid. This article proposes a framework for discrete environments called Iota explicit context representation (IECR). The framework involves representing each state …

Reachability Poorman Discrete-Bidding Games, Guy Avni, Tobias Meggendorfer, Suman Sadhukhan, Josef Tkadlec, Dorde Zikelic

Research Collection School Of Computing and Information Systems

We consider bidding games, a class of two-player zerosum graph games. The game proceeds as follows. Both players have bounded budgets. A token is placed on a vertex of a graph, in each turn the players simultaneously submit bids, and the higher bidder moves the token, where we break bidding ties in favor of Player 1. Player 1 wins the game iff the token visits a designated target vertex. Weconsider, for the first time, poorman discrete-bidding in which the granularity of the bids is restricted and the higher bid is paid to the bank. Previous work either did not impose …

Faster, Cheaper, And Better Cfd: A Case For Machine Learning To Augment Reynolds-Averaged Navier-Stokes, John Peter Romano Ii

Mechanical & Aerospace Engineering Theses & Dissertations

In recent years, the field of machine learning (ML) has made significant advances, particularly through applying deep learning (DL) algorithms and artificial intelligence (AI). The literature shows several ways that ML may enhance the power of computational fluid dynamics (CFD) to improve its solution accuracy, reduce the needed computational resources and reduce overall simulation cost. ML techniques have also expanded the understanding of underlying flow physics and improved data capture from experimental fluid dynamics.

This dissertation presents an in-depth literature review and discusses ways the field of fluid dynamics has leveraged ML modeling to date. The author selects and describes …

Machine Learning Prediction Of Hea Properties, Nicholas J. Beaver, Nathaniel Melisso, Travis Murphy

College of Engineering Summer Undergraduate Research Program

High-entropy alloys (HEA) are a very new development in the field of metallurgical materials. They are made up of multiple principle atoms unlike traditional alloys, which contributes to their high configurational entropy. The microstructure and properties of HEAs are are not well predicted with the models developed for more common engineering alloys, and there is not enough data available on HEAs to fully represent the complex behavior of these alloys. To that end, we explore how the use of machine learning models can be used to model the complex, high dimensional behavior in the HEA composition space. Based on our …

Ai For Search And Rescue - Locating A Missing Person, David Hernandez, Sai Rama Balakrishnan, Timmy Chin, Aditya Manikonda, Vasanth Pugalenthi

College of Engineering Summer Undergraduate Research Program

Building on the work done initially as a SURP 2021 project and continued through 2021-23, the focus for this summer project will be on the use of computer technology for locating a missing person. Over the last year, we developed the digital equivalents of about 30 paper-based S&R forms and the infrastructure to collect the respective information. In their current use, these paper forms are filled out by search teams, collected in a command post, and reviewed by search coordinators. This process is time-consuming, prone to errors and loss of information, and relies heavily on the experience, skills, and mental …

Instance-Specific Algorithm Configuration Via Unsupervised Deep Graph Clustering, Wen Song, Yi Liu, Zhiguang Cao, Yaoxin Wu, Qiqiang Li

Research Collection School Of Computing and Information Systems

Instance-specific Algorithm Configuration (AC) methods are effective in automatically generating high-quality algorithm parameters for heterogeneous NP-hard problems from multiple sources. However, existing works rely on manually designed features to describe training instances, which are simple numerical attributes and cannot fully capture structural differences. Targeting at Mixed-Integer Programming (MIP) solvers, this paper proposes a novel instances-specific AC method based on end-to-end deep graph clustering. By representing an MIP instance as a bipartite graph, a random walk algorithm is designed to extract raw features with both numerical and structural information from the instance graph. Then an auto-encoder is designed to learn dense …

Multi-Representation Variational Autoencoder Via Iterative Latent Attention And Implicit Differentiation, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Variational Autoencoder (VAE) offers a non-linear probabilistic modeling of user's preferences. While it has achieved remarkable performance at collaborative filtering, it typically samples a single vector for representing user's preferences, which may be insufficient to capture the user's diverse interests. Existing solutions extend VAE to model multiple interests of users by resorting a variant of self-attentive method, i.e., employing prototypes to group items into clusters, each capturing one topic of user's interests. Despite showing improvements, the current design could be more effective since prototypes are randomly initialized and shared across users, resulting in uninformative and non-personalized clusters.To fill the gap, …

Icl-D3ie: In-Context Learning With Diverse Demonstrations Updating For Document Information Extraction, Jiabang He, Lei Wang, Yi Hu, Ning Liu, Hui Liu, Xing Xu, Heng Tao Shen

Research Collection School Of Computing and Information Systems

arge language models (LLMs), such as GPT-3 and ChatGPT, have demonstrated remarkable results in various natural language processing (NLP) tasks with in-context learning, which involves inference based on a few demonstration examples. Despite their successes in NLP tasks, no investigation has been conducted to assess the ability of LLMs to perform document information extraction (DIE) using in-context learning. Applying LLMs to DIE poses two challenges: the modality and task gap. To this end, we propose a simple but effective in-context learning framework called ICL-D3IE, which enables LLMs to perform DIE with different types of demonstration examples. Specifically, we extract the …

Reinforcement Retrieval Leveraging Fine-Grained Feedback For Fact Checking News Claims With Black-Box Llm, Xuan Zhang, Wei Gao

Research Collection School Of Computing and Information Systems

Retrieval-augmented language models have exhibited promising performance across various areas of natural language processing (NLP), including fact-critical tasks. However, due to the black-box nature of advanced large language models (LLMs) and the non-retrieval-oriented supervision signal of specific tasks, the training of retrieval model faces significant challenges under the setting of black-box LLM. We propose an approach leveraging Fine-grained Feedback with Reinforcement Retrieval (FFRR) to enhance fact-checking on news claims by using black-box LLM. FFRR adopts a two-level strategy to gather fine-grained feedback from the LLM, which serves as a reward for optimizing the retrieval policy, by rating the retrieved documents …

Towards Explainable Harmful Meme Detection Through Multimodal Debate Between Large Language Models, Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma, Bo Wang, Ruichao Yang

Research Collection School Of Computing and Information Systems

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not explicitly conveyed through the surface text and image. However, existing harmful meme detection methods do not present readable explanations that unveil such implicit meaning to support their detection decisions. In this paper, we propose an explainable approach to detect harmful memes, achieved through reasoning over conflicting rationales from both harmless and harmful positions. Specifically, inspired by the powerful capacity of Large Language Models …

Improving Semantic Document Classification Accuracy By Integrating Human-Crafted Knowledge, Zachary Weinfeld, Lubomir Stanchev

College of Engineering Summer Undergraduate Research Program

Document classification is a pivotal task in various domains, warranting the development of robust algorithms. Among these, the Bidirectional Encoder Representations from Transformers (BERT) algorithm, introduced by Google, has proven to perform well when fine-tuned for the task at hand. Leveraging transformer architecture, BERT demonstrates stellar language understanding capabilities. However, the integration of BERT with a range of techniques has shown potential for further enhancing classification accuracy. This work investigates several techniques that leverage semantic understanding to improve the performance of document classification models trained with BERT. Specifically, we explore three methods. First, we will balance corpuses afflicted by imbalanced …

Integrating Human Expert Knowledge With Openai And Chatgpt: A Secure And Privacy-Enabled Knowledge Acquisition Approach, Ben Phillips

College of Engineering Summer Undergraduate Research Program

Advanced Large Language Models (LLMs) struggle to produce accurate results and preserve user privacy for use cases involving domain-specific knowledge. A privacy-preserving approach for leveraging LLM capabilities on domain-specific knowledge could greatly expand the use cases of LLMs in a variety of disciplines and industries. This project explores a method for acquiring domain-specific knowledge for use with GPT3 while protecting sensitive user information with ML-based text-sanitization.

Ethics And Social Justice For Ai In Data Science, Arya Ramchander, Kylene Nicole Landenberger

College of Engineering Summer Undergraduate Research Program

The advances of AI raise several critical questions about human values and ethics, highlighting the need for researchers and developers to consider the ethical implications and the risks of neglecting them. In the past few years, student researchers have developed an AI model that allows users to test their surveys for possible breaches of subject confidentiality. This allows the users to gauge the ethicality of their proposal. This summer, we have expanded on this research and launched an interactive model for students and researches to assess their current work for ethical and social justice implications. Using Langchain and Figma, we …

A Gentle Introduction To Chatgpt, Steven W. Holloway

Libraries

A guest lecture on the state of commercial generative transformer technology, mid-2023, to a general audience at Staunton Public Library.

Style Transfer Network For Generating Opera Makeup Details, Fengquan Zhang, Duo Cao, Xiaohan Ma, Baijun Chen, Jiangxiao Zhang

Journal of System Simulation

Abstract: To address the problem of the loss of local style details in cross-domain image simulation, a ChinOperaGAN network framework suitable for opera makeup is designed from the perspective of protecting the excellent traditional culture. In order to solve the style translation of differences in two image domains, multiple overlapping local adversarial discriminators are proposed in the generative adversarial network. Since paired opera makeup data are difficult to obtain, a synthetic image is generated by combining the source image makeup mapping to effectively guide the transfer of local makeup details between images. In view of the characteristics of opera makeup …

Research On Artificial Population Generation And Application Based On Genetic Algorithm, Hongli Zhang, Jingshuang Deng

Journal of System Simulation

Abstract: High-precision micro-population data are one of the key basic data for simulation systems such as disease spread, traffic travel, and emergency events. In reality, computer-generated artificial populations are often used for simulation. Due to computational efficiency and standardization of generation steps, the iterative proportional fitting method is currently used for artificial population synthesis. However, it has strict requirements on basic data and faces zero-unit and data representational deviation problems, and it fails to guarantee the fitting at the individual and family levels at the same time. In order to overcome this deficiency, an improved genetic algorithm using a simulated …

Data Generation Model-Based Synthetic Sample Imputation Method, Yulin He, Jiaqi Chen, Hepeng Xu, Zhexue Huang, Jianfei Yin

Journal of System Simulation

Abstract: In order to solve the problem of inconsistent probability distribution between synthetic samples by imputation and real samples, a data generation model-based synthetic sample imputation (DGM-SSI) method is proposed. The data generation model of real samples is constructed based on the Gaussian mixture model, and the number of corresponding components of the Gaussian mixture model is determined by the multi-model fusion strategy. The synthetic samples required for model imputation are generated by using the data obtained from the real samples. Specifically, the components of the data generation model and their weights are used to control the generation of synthetic …

Construction And Application Of Digital Twin System For Optical Fiber Secondary Coating Workshop, Biao Yuan, Yourui Huang, Shanyong Xu, Xue Rong

Journal of System Simulation

Abstract: In order to solve the problem that the current optical fiber secondary coating workshop has inferior intelligence and low digital degree, a three-dimensional (3D) visual monitoring and fault diagnosis method for the optical fiber secondary coating workshop based on digital twin (DT) is proposed. In view of the equipment in the optical fiber secondary coating workshop, combined with the workshop production process and equipment operation mechanism, the digital modeling of all physical properties of the optical fiber secondary coating workshop is carried out, and the virtual twin scene is constructed. Real-time mapping between the virtual workshop and the physical …

3d Garment Collision Simulation Based On Human Skeletal Features, Yuanyuan Chen, Yongjian Huai, Xiaoying Nie, Ke Lang

Journal of System Simulation

Abstract: In order to enhance the realism of garment and human body collision in real-time fabric simulation, an automated human body fitting collision method based on the bounding box and mesh method is proposed. According to the human skeletal structure and garment type, the skeletal information involved in collision simulation is effectively optimized, so as to better obtain the feature points of the human body and semantically segment them. According to the characteristics of skinning animation, simple capsule colliders and mesh colliders are generated to fit the geometric shape of the human body, and the dynamic following of colliders is …

Simulation Research On Multi-Antenna Coupled Radiation Of Launch Vehicle In Tower, Fen Zhang, Tao Yu, Yong Han, Longwei He

Journal of System Simulation

Abstract: The signal radiation of the launch vehicle wireless system test in the closed tower of the launching site is very complex. In order to further study the antenna radiation characteristics, especially the multi-antenna coupled radiation in the whole vehicle state, a multi antenna model with tower-vehicle body is established in this paper based on UG modeling technology and Altair Hyper Works 2017 electromagnetic compatibility simulation platform. It involves the method of moments-physical optics (MOM-PO) hybrid algorithm and delineates different calculation areas for different scale divisions, so as to solve quickly and accurately electromagnetic parameters of multi-antenna coupled radiation. The …

Aircraft Assignment Method For Optimal Utilization Of Maintenance Intervals, Runxia Guo, Yifu Wang

Journal of System Simulation

Abstract: The aircraft assignment problem is studied from a maintenance assurance perspective. In order to ensure its continuous airworthiness, civil aircraft are required to perform maintenance tasks, i. e., scheduled inspections, at specified intervals. The scheduled inspection interval is usually controlled by the number of flight cycles (FC), flight hours (FH), or flight days (FD), whichever comes first. In order to make balanced use of the inspection interval, an aircraft assignment model for a given fleet size is developed to optimize the maintenance interval utilization, and it is solved by a reinforcement learning algorithm to minimize the variance of the …

A Deep Learning-Based Object Detection Framework For Automatic Asphalt Pavement Patch Detection Using Laser Profiling Images, Ibrahim Hassan Syed, Susan Mckeever Dr., Kieran Feighan, David Power, Dympna O'Sullivan

Conference papers

Road maintenance and the early detection of road defects rely on routine pavement inspections. While advanced 3D laser profiling systems have the capability to automatically identify certain types of distress such as cracks and ruts, more complex pavement damage, including patches, often require manual identification. To address this limitation, this study proposes an automated patch detection system that employs object detection techniques. The results demonstrate the ability of object detection models to accurately identify patches in laser profiling images, indicating that the proposed approach has the capability to significantly enhance automation in visual inspection processes. This has the potential for …