Computer Sciences Commons^™

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 …

Gramseq-Dta: A Grammar-Based Drug-Target Affinity Prediction Approach Fusing Gene Expression Information, Kasul Debnath, Pratip Rana, Preetam Ghosh

Computer Science Faculty Publications

Drug–target affinity (DTA) prediction is a critical aspect of drug discovery. The meaningful representation of drugs and targets is crucial for accurate prediction. Using 1D string-based representations for drugs and targets is a common approach that has demonstrated good results in drug–target affinity prediction. However, these approach lacks information on the relative position of the atoms and bonds. To address this limitation, graph-based representations have been used to some extent. However, solely considering the structural aspect of drugs and targets may be insufficient for accurate DTA prediction. Integrating the functional aspect of these drugs at the genetic level can enhance …

Ensemble Learning Models For Large-Scale Time Series Forecasting In Supply Chain, Minjuan Zhang

Dissertations

Machine learning and AI techniques are transforming supply chain forecasting, driven by the expanding availability of data assets. These advanced methods offer powerful opportunities to optimize management processes, reduce operational costs, and enhance strategic decision-making, which is crucial for enterprise success. However, conventional statistical approaches, such as Autoregressive Integrated Moving Average Models (ARIMA), dynamic regression, and Unobserved Component Models (UCMs)—which have long dominated time series forecasting—often fall short in accuracy and scalability. These traditional models face limitations in batch processing, handling large-scale data, addressing uncertainty-induced disruptions, and synchronizing demand-supply scenarios.

To address these challenges, a novel class of AI-powered ensemble …

Decoding Neural Networks: An Information-Theoretic Guide To Interpretability, Error Analysis And Efficiency, Mackenzie J. Meni

Theses and Dissertations

This dissertation addresses critical challenges in neural network design by leveraging entropy-based techniques to improve model efficiency, interpretability, and bias reduction. Focusing on the unique demands of computer vision applications, particularly object detection and classification for real-time systems, this work introduces a series of innovative methods centered on information theory. At the core of these methods is the Probabilistic Explanations of Entropic Knowledge (PEEK) framework, a tool developed to analyze and visualize entropy distributions across feature maps. PEEK offers insights into information flow within neural networks, making it possible to pinpoint layers that contribute meaningfully to decision-making or identify those …

A Comprehensive Survey On Relation Extraction: Recent Advances And New Frontiers, Xiaoyan Zhao, Yang Deng, Min Yang, Lingzhi Wang, Rui Zhang, Hong Cheng, Wai Lam, Ying Shen, Ruifeng Xu

Research Collection School Of Computing and Information Systems

Relation extraction (RE) involves identifying the relations between entities from underlying content. RE serves as the foundation for many natural language processing (NLP) and information retrieval applications, such as knowledge graph completion and question answering. In recent years, deep neural networks have dominated the field of RE and made noticeable progress. Subsequently, the large pre-trained language models (PLMs) have taken the state-of-the-art RE to a new level. This survey provides a comprehensive review of existing deep learning techniques for RE. First, we introduce RE resources, including datasets and evaluation metrics. Second, we propose a new taxonomy to categorize existing works …

Latent Representation Learning For Geospatial Entities, Ween Jiann Lee, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Representation learning has been instrumental in the success of machine learning, offering compact and performant data representations for diverse downstream tasks. In the spatial domain, it has been pivotal in extracting latent patterns from various data types, including points, polylines, polygons, and networked structures. However, existing approaches often fall short of explicitly capturing both semantic and spatial information, relying on proxies and synthetic features. This article presents GeoNN, a novel graph neural network-based model designed to learn spatially-aware embeddings for geospatial entities. GeoNN leverages edge features generated from geodesic functions, dynamically selecting relevant features based on relative locations. It introduces …

High Prevalence Of Artifacts In Optical Coherence Tomography With Adequate Signal Strength, Wei-Chun Lin, Aaron Coyner, Charles Amankwa, Abigail Lucero, Gadi Wollstein, Joel Schuman, Hiroshi Ishikawa

Wills Eye Hospital Papers

PURPOSE: This study aims to investigate the prevalence of artifacts in optical coherence tomography (OCT) images with acceptable signal strength and evaluate the performance of supervised deep learning models in improving OCT image quality assessment.

METHODS: We conducted a retrospective study on 4555 OCT images from 546 patients, with each image having an acceptable signal strength (≥6). A comprehensive analysis of prevalent OCT artifacts was performed, and five pretrained convolutional neural network models were trained and tested to infer images based on quality.

RESULTS: Our results showed a high prevalence of artifacts in OCT images with acceptable signal strength. Approximately …

Achieving Domain-Independent Certified Robustness Via Knowledge Continuity, Alan Wenyuan Sun

Computer Science Senior Theses

We present knowledge continuity, a novel definition inspired by Lipschitz continuity which aims to certify the robustness of neural networks across input domains (such as continuous and discrete domains in vision and language, respectively). Most existing approaches that seek to certify robustness, especially Lipschitz continuity, lie within the continuous domain with norm and distribution-dependent guarantees. In contrast, our proposed definition yields certification guarantees that depend only on the loss function and the intermediate learned metric spaces of the neural network. These bounds are independent of domain modality, norms, and distribution. We further demonstrate that the expressiveness of a model …

Text-Attributed Graph Representation Learning : Methods, Applications, And Challenges, Ce Zhang, Menglin Yang, Rex Ying, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Text documents are usually connected in a graph structure, resulting in an important class of data named text-attributed graph, e.g., paper citation graph and Web page hyperlink graph. On the one hand, Graph Neural Networks (GNNs) consider text in each document as general vertex attribute and do not specifically deal with text data. On the other hand, Pre-trained Language Models (PLMs) and Topic Models (TMs) learn effective document embeddings. However, most models focus on text content in each single document only, ignoring link adjacency across documents. The above two challenges motivate the development of text-attributed graph representation learning, combining GNNs …

Combining Empirical And Physics-Based Models For Solar Wind Prediction, Rob Johnson, Soukaina Filali Boubrahimi, Omar Bahri, Shah Muhammad Hamdi

Computer Science Faculty and Staff Publications

Solar wind modeling is classified into two main types: empirical models and physics-based models, each designed to forecast solar wind properties in various regions of the heliosphere. Empirical models, which are cost-effective, have demonstrated significant accuracy in predicting solar wind at the L1 Lagrange point. On the other hand, physics-based models rely on magnetohydrodynamics (MHD) principles and demand more computational resources. In this research paper, we build upon our recent novel approach that merges empirical and physics-based models. Our recent proposal involves the creation of a new physics-informed neural network that leverages time series data from solar wind predictors to …

Mathematically Rigorous Deep Learning Paradigms For Data-Driven Scientific Modeling, Owen Nicholas Davis

Mathematics & Statistics ETDs

This dissertation explores the crucial role of data-driven modeling in science and engineering, with a focus on developing surrogate models to accelerate large-scale computational tasks, aiding in both outer-loop functions like uncertainty quantification and expensive inner-loop tasks within broader computational frameworks. Challenges arise with increased problem dimension and sparse, noisy training data, particularly significant when constructing surrogates for very expensive computational models where acquiring sufficient high-fidelity training data is unfeasible. In such scenarios, training surrogates from an ensemble of multifidelity information sources of varying accuracy and cost becomes essential. We emphasize neural network-based modeling paradigms, which are flexible in integrating …

Detecting Anomalies In Time Series Using Kernel Density Approaches, Robin Frehner, Kesheng Wu, Alexander Sim, Jinoh Kim

Faculty Publications

This paper introduces a novel anomaly detection approach tailored for time series data with exclusive reliance on normal events during training. Our key innovation lies in the application of kernel-density estimation (KDE) to scrutinize reconstruction errors, providing an empirically derived probability distribution for normal events post-reconstruction. This non-parametric density estimation technique offers a nuanced understanding of anomaly detection, differentiating it from prevalent threshold-based mechanisms in existing methodologies. In post-training, events are encoded, decoded, and evaluated against the estimated density, providing a comprehensive notion of normality. In addition, we propose a data augmentation strategy involving variational autoencoder-generated events and a smoothing …

Group Convolutional Decoders For Toric Codes, Jim Wang

Theses and Dissertations

Quantum Error Correction (QEC) enables both industrial and defense applications of quantum computing. Toric codes and other quantum Low-Density Parity-Check (LDPC) codes are promising and well-researched methods of QEC. However, their decoding cost increases exponentially with a computer’s qubit count. Neural Network (NN) decoders have been shown to decode a code’s error syndrome both accurately and fast enough for a real-time error correcting scheme. Recent key developments introduced Convolutional Neural Network (CNN) to implement a translationally equivariant decoder for a toric code. These CNN decoders both outperform NN decoders and require less training data. This research applies a Group Convolutional …

Continual Online Learning-Based Optimal Tracking Control Of Nonlinear Strict-Feedback Systems: Application To Unmanned Aerial Vehicles, Irfan Ganie, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

A novel optimal trajectory tracking scheme is introduced for nonlinear continuous-time systems in strict feedback form with uncertain dynamics by using neural networks (NNs). The method employs an actor-critic-based NN back-stepping technique for minimizing a discounted value function along with an identifier to approximate unknown system dynamics that are expressed in augmented form. Novel online weight update laws for the actor and critic NNs are derived by using both the NN identifier and Hamilton-Jacobi-Bellman residual error. A new continual lifelong learning technique utilizing the Fisher Information Matrix via Hamilton-Jacobi-Bellman residual error is introduced to obtain the significance of weights in …

U.S. Army Cadet Command Branch Prediction Model, Daniel M. Krizan

Theses and Dissertations

The current system for providing US Army ROTC cadets their branches leaves significant uncertainty until the final pronouncement of branch assigned. This uncertainty can be alleviated by providing a prediction model for cadets to input personal data and desired branch to identify likelihood of receiving the request. This thesis produces a machine learning model capable of producing branch prediction for cadets.

Conditional Neural Heuristic For Multiobjective Vehicle Routing Problems, Mingfeng Fan, Yaoxin Wu, Zhiguang Cao, Wen Song, Guillaume Sartoretti, Huan Liu, Guohua Wu

Research Collection School Of Computing and Information Systems

Existing neural heuristics for multiobjective vehicle routing problems (MOVRPs) are primarily conditioned on instance context, which failed to appropriately exploit preference and problem size, thus holding back the performance. To thoroughly unleash the potential, we propose a novel conditional neural heuristic (CNH) that fully leverages the instance context, preference, and size with an encoder–decoder structured policy network. Particularly, in our CNH, we design a dual-attention-based encoder to relate preferences and instance contexts, so as to better capture their joint effect on approximating the exact Pareto front (PF). We also design a size-aware decoder based on the sinusoidal encoding to explicitly …

An Investigation Into The Role Of Machine Learning And Deep Learning Models As A Means Of Leveraging The Ever-Expanding Volume Of Astronomical Data To Automate Stellar Classification., Gerard Heraghty

ICT

This research investigates the use of machine learning and neural network models for automated stellar classification in large astronomical surveys, addressing challenges posed by the increasing volume of data. Using the MK scheme as the classification standard, the study focused on spectroscopic data and balanced the dataset using SMOTE techniques to handle class imbalances. Various models, including Random Forest, SVM, MLP, and CNN, were trained and compared for classifying MK main and sub-classes. CNN achieved the highest accuracy (93.86%) for main class classification, while SVM excelled at sub-class classification (63.23%) on balanced datasets. However, when tested on real-world SDSS data, …

Integrative Machine Learning Approaches For Enhanced Classification Of Genomic Sequences: A Next-Generation Sequencing Perspective, Sujatha Alla, Nagesh Bheesetty, Sai Gireesh Komaragiri, Prasanthi Chidipudi, Joshit Mohanty, Sathish Kumar Chintala, Jubin Thomas, Jayapal Vummadi, Hemanth Volikatla, Navin Kamuni

Engineering Management & Systems Engineering Faculty Publications

The advent of Next-Generation Sequencing (NGS) techniques has revolutionized genomic research by enabling the rapid sequencing of DNA and RNA. This data can be used for various applications, including genome sequencing, transcriptome profiling, metagenomics, and epigenetics studies. For this study, DNA classifier dataset was extracted from UCI repository of machine learning databases. This vast amount of genomic data necessitates the development of sophisticated machine learning (ML) models for effective classification and analysis. This study presents a comprehensive comparison of various ML models, including Support Vector Machines (SVM), Random Forests (RF), and Neural Networks (NNs), approaches, in classifying genomic data. We …

On Generative Models And Joint Architectures For Document-Level Relation Extraction, Aviv Brokman

Theses and Dissertations--Statistics

Biomedical text is being generated at a high rate in scientific literature publications and electronic health records. Within these documents lies a wealth of potentially useful information in biomedicine. Relation extraction (RE), the process of automating the identification of structured relationships between entities within text, represents a highly sought-after goal in biomedical informatics, offering the potential to unlock deeper insights and connections from this vast corpus of data. In this dissertation, we tackle this problem with a variety of approaches.

We review the recent history of the field of document-level RE. Several themes emerge. First, graph neural networks dominate the …

Deep Transfer Learning-Based Bird Species Classification Using Mel Spectrogram Images, Mrinal Kanti Baowaly, Bisnu Chandra Sarkar, Md.Abul Ala Walid, Md. Martuza Ahamad, Bikash Chandra Singh, Eduardo Silva Alvarado, Imran Ashraf, Md. Abdus Samad

School of Cybersecurity Faculty Publications

The classification of bird species is of significant importance in the field of ornithology, as it plays an important role in assessing and monitoring environmental dynamics, including habitat modifications, migratory behaviors, levels of pollution, and disease occurrences. Traditional methods of bird classification, such as visual identification, were time-intensive and required a high level of expertise. However, audio-based bird species classification is a promising approach that can be used to automate bird species identification. This study aims to establish an audio-based bird species classification system for 264 Eastern African bird species employing modified deep transfer learning. In particular, the pre-trained EfficientNet …

Classification Of Instructional Activities In Classroom Videos Using Neural Networks, Jonathan K. Foster, Matthew Korban, Peter Youngs, Ginger S. Watson, Scott T. Acton

VMASC Publications

Classroom videos have become an integral part of classroom observation and instructional quality studies. Researchers encounter substantial financial and time-consuming costs gathering trained personnel to catalogue and analyze a large quantity (i.e., hundreds of hours) of classroom videos. In this chapter, we argue that deep-learning neural networks have potential to help with these tasks by detecting features of instruction in videos. We evaluated the performance of three neural networks in detecting instructional activities in classroom videos. The video dataset included a total of forty-six hours, which was evenly split between elementary mathematics and English language arts lesson recordings. Results showed …

Automatic Classification Of Activities In Classroom Videos, Jonathan K. Foster, Matthew Korban, Peter Youngs, Ginger S. Watson, Scott T. Acton

VMASC Publications

Classroom videos are a common source of data for educational researchers studying classroom interactions as well as a resource for teacher education and professional development. Over the last several decades emerging technologies have been applied to classroom videos to record, transcribe, and analyze classroom interactions. With the rise of machine learning, we report on the development and validation of neural networks to classify instructional activities using video signals, without analyzing speech or audio features, from a large corpus of nearly 250 h of classroom videos from elementary mathematics and English language arts instruction. Results indicated that the neural networks performed …

Advancing Household Robotics: Deep Interactive Reinforcement Learning For Efficient Training And Enhanced Performance, Arpita Soni, Sujatha Alla, Suresh Dodda, Hemanth Volikatla

Engineering Management & Systems Engineering Faculty Publications

The market for domestic robots—made to perform household chore, is growing as these robots relieve people of everyday responsibilities. Domestic robots are generally welcomed for their role in easing human labour, in contrast to industrial robots, which are frequently criticised for displacing human workers. But before these robots can carry out domestic chores, they need to become proficient in a number of minor activities, such as recognizing their surroundings, making decisions, and picking up on human behaviours. Reinforcement learning, or RL, has emerged as a key robotics technology that enables robots to interact with their environment and learn how to …

Latent Space Dynamics Learning For Stiff Collisional-Radiative Models, Xuping Xie, Qi Tang, Xianzhu Tang

Mathematics & Statistics Faculty Publications

In this work, we propose a data-driven method to discover the latent space and learn the corresponding latent dynamics for a collisional-radiative (CR) model in radiative plasma simulations. The CR model, consisting of high-dimensional stiff ordinary differential equations, must be solved at each grid point in the configuration space, leading to significant computational costs in plasma simulations. Our method employs a physics-assisted autoencoder to extract a low-dimensional latent representation of the original CR system. A flow map neural network is then used to learn the latent dynamics. Once trained, the reduced surrogate model predicts the entire latent dynamics given only …

Unlocking The Potential Of Simulated Hyperspectral Imaging In Agro Environmental Analysis: A Comprehensive Study Of Algorithmic Approaches, Shafaq Khan, Munir Majdalawieh, Boubakeur Boufama, Yajan Sharma, Ashwitha Basani

All Works

This study focuses on identifying and evaluating the severity of powdery mildew disease in tomato plants. The uniqueness of this work lies in combining the imaging and advanced deep learning methods to develop a technique that transforms Red Green Blue (RGB) images into Simulated Hyperspectral Images (SHSI) to perform spectral and spatial analysis for precise detection and assessment of powdery mildew severity, thereby enhancing disease management. Furthermore, this research evaluates three advanced pre-trained VGG16 models, ResNet50 and EfficientNet-B7 algorithms for image preprocessing and feature extraction. Extracted features are passed to a neural network generator model to convert RGB image features …

Skipresnet: Crop And Weed Recognition Based On The Improved Resnet, Wenyi Hu, Tian Chen, Chunjie Lan, Shan Liu, Lirong Yin

Electrical & Computer Engineering Faculty Publications

Weeds have a detrimental effect on crop yield. However, the prevailing chemical weed control methods cause pollution of the ecosystem and land. Therefore, it has become a trend to reduce dependence on herbicides; realize a sustainable, intelligent weed control method; and protect the land. In order to realize intelligent weeding, efficient and accurate crop and weed recognition is necessary. Convolutional neural networks (CNNs) are widely applied for weed and crop recognition due to their high speed and efficiency. In this paper, a multi-path input skip-residual network (SkipResNet) was put forward to upgrade the classification function of weeds and crops. It …

Scene Classification Of Remote Sensing Image Based On Multi-Path Reconfigurable Neural Network, Wenyi Hu, Chunjie Lan, Tian Chen, Shan Liu, Lirong Yin, Lei Wang

Electrical & Computer Engineering Faculty Publications

Land image recognition and classification and land environment detection are important research fields in remote sensing applications. Because of the diversity and complexity of different tasks of land environment recognition and classification, it is difficult for researchers to use a single model to achieve the best performance in scene classification of multiple remote sensing land images. Therefore, to determine which model is the best for the current recognition classification tasks, it is often necessary to select and experiment with many different models. However, finding the optimal model is accompanied by an increase in trial-and-error costs and is a waste of …

Identifying New Cancer Genes Based On The Integration Of Annotated Gene Sets Via Hypergraph Neural Networks, Chao Deng, Hong-Dong Li, Li-Shen Zhang, Yiwei Liu, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

Motivation

Identifying cancer genes remains a significant challenge in cancer genomics research. Annotated gene sets encode functional associations among multiple genes, and cancer genes have been shown to cluster in hallmark signaling pathways and biological processes. The knowledge of annotated gene sets is critical for discovering cancer genes but remains to be fully exploited.

Results

Here, we present the DIsease-Specific Hypergraph neural network (DISHyper), a hypergraph-based computational method that integrates the knowledge from multiple types of annotated gene sets to predict cancer genes. First, our benchmark results demonstrate that DISHyper outperforms the existing state-of-the-art methods and highlight the advantages of …

Forecasting Crude Oil Price Using Multiple Factors, Hind Aldabagh, Xianrong Zheng, Mohammad Najand, Ravi Mukkamala

Computer Science Faculty Publications

In this paper, we predict crude oil price using various factors that may influence its price. The factors considered are physical market, financial, and trading market factors, including seven key factors and the dollar index. Firstly, we select the main factors that may greatly influence the prices. Then, we develop a hybrid model based on a convolutional neural network (CNN) and long short-term memory (LSTM) network to predict the prices. Lastly, we compare the CNN–LSTM model with other models, namely gradient boosting (GB), decision trees (DTs), random forests (RFs), neural networks (NNs), CNN, LSTM, and bidirectional LSTM (Bi–LSTM). The empirical …

Bayesian Neural Netwok Variational Autoencoder Inverse Mapper (Bnn-Vaim) And Its Application In Compton Form Factors Extraction, Md Fayaz Bin Hossen, Tareq Alghamdi, Manal Almaeen, Yaohang Li

Computer Science Faculty Publications

We extend the Variational Autoencoder Inverse Mapper (VAIM) framework for the inverse problem of extracting Compton Form Factors (CFFs) from deeply virtual exclusive reactions, such as the unpolarized Deeply virtual exclusive scattering (DVCS) cross section. VAIM is an end-to-end deep learning framework to address the solution ambiguity issue in ill-posed inverse problems, which comprises of a forward mapper and a backward mapper to simulate the forward and inverse processes, respectively. In particular, we incorporate Bayesian Neural Network (BNN) into the VAIM architecture (BNN-VAIM) for uncertainty quantification. By sampling the weights and biases distributions of the BNN in the backward mapper …