Artificial Intelligence and Robotics Commons^™

Energy-Aware Sensor Fusion Architecture For Autonomous Channel Robot Navigation In Constrained Environments, Mohamed Shili, Hicham Chaoui, Khaled Nouri

Electrical & Computer Engineering Faculty Publications

Navigating autonomous robots in confined channels is inherently challenging due to limited space, dynamic obstacles, and energy constraints. Existing sensor fusion strategies often consume excessive power because all sensors remain active regardless of environmental conditions. This paper presents an energy-aware adaptive sensor fusion framework for channel robots that deploys RGB cameras, laser range finders, and IMU sensors according to environmental complexity. Sensor data are fused using an adaptive Extended Kalman Filter (EKF), which selectively integrates multi-sensor information to maintain high navigation accuracy while minimizing energy consumption. An energy management module dynamically adjusts sensor activation and computational load, enabling significant reductions …

Evaluating The Emotional Accuracy Of Ai-Generated Facial Expressions In Neurotypical Individuals, Antonio Pagán, Katherine A Loveland, Ronald Acierno

Faculty, Staff and Student Publications

This study examines the ability of generative artificial intelligence to produce facial expressions representing basic emotions in a neutral context using black-and-white cartoon imagery. Mentalization, the capacity to recognize and interpret one’s own and others’ mental states, is critical for social interaction and emotional regulation. We explored the emotional validation of artificial intelligence (AI)-generated images by assessing the agreement between human interpretations of emotions and those generated by an AI model. Thirty-four participants evaluated images depicting six basic emotions: sadness, anger, happiness, surprise, fear, and disgust. Our findings revealed significant variability in human agreement, with higher concordance for sadness, anger, …

Machine Learning Predicting Acute Pain And Opioid Dose In Radiation Treated Oropharyngeal Cancer Patients, Vivian Salama, Laia Humbert-Vidan, Brandon Godinich, Kareem A Wahid, Dina M Elhabashy, Mohamed A Naser, Renjie He, Abdallah S R Mohamed, Ariana J Sahli, Katherine A Hutcheson, Gary Brandon Gunn, David I Rosenthal, Clifton D Fuller, Amy C Moreno

Faculty, Staff and Student Publications

Introduction: Acute pain is common among oral cavity/oropharyngeal cancer (OCC/OPC) patients undergoing radiation therapy (RT). This study aimed to predict acute pain severity and opioid doses during RT using machine learning (ML), facilitating risk-stratification models for clinical trials.

Methods: A retrospective study examined 900 OCC/OPC patients treated with RT during 2017-2023. Pain intensity was assessed using NRS (0-none, 10-worst) and total opioid doses were calculated using morphine equivalent daily dose (MEDD) conversion factors. Analgesics efficacy was assessed using combined pain intensity and total MEDD. ML predictive models were developed and validated, including Logistic Regression (LR), Support Vector Machine (SVM), Random …

Financial Named Entity Recognition: How Far Can Llm Go?, Yi-Te Lu, Yintong Huo

Research Collection School Of Computing and Information Systems

The surge of large language models (LLMs) has revolutionized the extraction and analysis of crucial information from a growing volume of financial statements, announcements, and business news. Recognition for named entities to construct structured data poses a significant challenge in analyzing financial documents and is a foundational task for intelligent financial analytics. However, how effective are these generic LLMs and their performance under various prompts are yet need a better understanding. To fill in the blank, we present a systematic evaluation of state-of-the-art LLMs and prompting methods in the financial Named Entity Recognition (NER) problem. Specifically, our experimental results highlight …

Toward Embodied Navigation Through Vision And Language, Muraleekrishna Gopinathan

Theses: Doctorates and Masters

Embodied AI is a challenging but exciting field in which a robot learns to interact with human-living spaces to perform various tasks. This thesis studies the embodied navigation problem in which a robotic agent navigates in a previously unseen indoor environment based on a challenging task. In particular, the Vision-and-Language Navigation (VLN) task requires a robot to navigate based on a descriptive human-language instruction. This thesis aims to improve VLN agents on four key aspects - their understanding of the environment, training via additional data, correcting navigational errors, and predicting the layout of the environment for better planning.

First, we …

Defending Federated Recommender Systems Against Untargeted Attacks: A Contribution-Aware Robust Aggregation Scheme, Ruicheng Liang, Yuanchun Jiang, Feida Zhu, Ling Cheng, Huiwen Liu

Research Collection School Of Computing and Information Systems

Federated recommender systems (FedRSs) effectively tackle the tradeoff between recommendation accuracy and privacy preservation. However, recent studies have revealed severe vulnerabilities in FedRSs, particularly against untargeted attacks seeking to undermine their overall performance. Defense methods employed in traditional recommender systems are not applicable to FedRSs, and existing robust aggregation schemes for other federated learning-based applications have proven ineffective in FedRSs. Building on the observation that malicious clients contribute negatively to the training process, we design a novel contribution-aware robust aggregation scheme to defend FedRSs against untargeted attacks, named contribution-aware Bayesian knowledge distillation aggregation (ConDA), comprising two key components for the …

Lara : A Light And Anti-Overfitting Retraining Approach For Unsupervised Time Series Anomaly Detection, Feiyi Chen, Zhen Qin, Mengchu Zhou, Yingying Zhang, Shuiguang Deng, Lunting Fan, Guansong Pang, Qingsong Wen

Research Collection School Of Computing and Information Systems

Most of current anomaly detection models assume that the normal pattern remains the same all the time. However, the normal patterns of web services can change dramatically and frequently over time. The model trained on old-distribution data becomes outdated and ineffective after such changes. Retraining the whole model whenever the pattern is changed is computationally expensive. Further, at the beginning of normal pattern changes, there is not enough observation data from the new distribution. Retraining a large neural network model with limited data is vulnerable to overfitting. Thus, we propose a Light Anti-overfitting Retraining Approach (LARA) based on deep variational …

Fuzzing Drones For Anomaly Detection: A Systematic Literature Review, Vikas Kumar Malviya, Wei Minn, Lwin Khin Shar, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Drones, also referred to as Unmanned Aerial Vehicles (UAVs), are becoming popular today due to their uses in different fields and recent technological advancements which provide easy control of UAVs via mobile apps. However, UAVs may contain vulnerabilities or software bugs that cause serious safety and security concerns. For example, the communication protocol used by the UAV may contain authentication and authorization vulnerabilities, which may be exploited by attackers to gain remote access over the UAV. Drones must therefore undergo extensive testing before being released or deployed to identify and fix any software bugs or security vulnerabilities. Fuzzing is one …

Measuring Model Alignment For Code Clone Detection Using Causal Interpretation, Shamsa Abid, Xuemeng Cai, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Deep Neural Network-based models have demonstrated high accuracy for semantic code clone detection. However, the lack of generalization poses a threat to the trustworthiness and reliability of these models. Furthermore, the black-box nature of these models makes interpreting the model’s decisions very challenging. Currently, there is only a limited understanding of the semantic code clone detection behavior of existing models. There is a lack of transparency in understanding how a model identifies semantic code clones and the exact code components influencing its prediction. In this paper, we introduce the use of a causal interpretation framework based on the Neyman-Rubin causal …

A Review Of Chinese Sentiment Analysis: Subjects, Methods, And Trends, Zhaoxia Wang, Donghao Huang, Jingfeng Cui, Xinyue Zhang, Seng-Beng Ho, Erik Cambria

Research Collection School Of Computing and Information Systems

Sentiment analysis has emerged as a prominent research domain within the realm of natural language processing, garnering increasing attention and a growing body of literature. While numerous literature reviews have examined sentiment analysis techniques, methods, topics and applications, there remains a gap in the literature concerning thematic trends and research methodologies in sentiment analysis, particularly in the context of Chinese text. This study addresses this gap by presenting a comprehensive survey dedicated to the progression of research subjects, methods and trends in sentiment analysis of Chinese text. Employing a framework that combines keyword co-occurrence analysis with a sophisticated community detection …

Llms-Based Augmentation For Domain Adaptation In Long-Tailed Food Datasets, Qing Wang, Chong-Wah Ngo, Ee-Peng Lim, Qianru Sun

Research Collection School Of Computing and Information Systems

Training a model for food recognition is challenging because the training samples, which are typically crawled from the Internet, are visually different from the pictures captured by users in the free-living environment. In addition to this domain-shift problem, the real-world food datasets tend to be long-tailed distributed and some dishes of different categories exhibit subtle variations that are difficult to distinguish visually. In this paper, we present a framework empowered with large language models (LLMs) to address these challenges in food recognition. We first leverage LLMs to parse food images to generate food titles and ingredients. Then, we project the …

Interactive Video Search With Multi-Modal Llm Video Captioning, Yu-Tong Cheng, Jiaxin Wu, Zhixin Ma, Jiangshan He, Xiao-Yong Wei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Cross-modal representation learning is essential for interactive text-to-video search tasks. However, the representation learning is limited by the size and quality of video-caption pairs. To improve the search accuracy, we propose to enlarge the size of available video-caption pairs by leveraging multi-model LLM on video captioning. Specifically, we use LLM to generate video captions for a large video collection (i.e., WebVid dataset) and use the generated video-caption pairs to pre-train a text-to-video search model. Additionally, we use LLM to generate fine-grained captions for test video collections to enable text-to-caption retrieval. Furthermore, we build a semantic overview of the retrieved rank …

Weakly-Supervised Semantic Segmentation With Image-Level Labels: From Traditional Models To Foundation Models, Zhaozheng Chen, Qianru Sun

Research Collection School Of Computing and Information Systems

The rapid development of deep learning has driven significant progress in image semantic segmentation—a fundamental task in computer vision. Semantic segmentation algorithms often depend on the availability of pixel-level labels (i.e., masks of objects), which are expensive, time consuming, and labor intensive. Weakly supervised semantic segmentation (WSSS) is an effective solution to avoid such labeling. It utilizes only partial or incomplete annotations and provides a cost-effective alternative to fully supervised semantic segmentation. In this article, our focus is on the WSSS with image-level labels, which is the most challenging form of WSSS. Our work has two parts. First, we conduct …

Synthesizing Multi-Person And Rare Pose Images For Human Pose Estimation, Liuqing Zhao, Zichen Tian, Zou Peng, Richang Hong, Qianru Sun

Research Collection School Of Computing and Information Systems

Human pose estimation (HPE) models underperform in recognizing rare poses because they suffer from data imbalance problems (i.e., there are few image samples for rare poses) in their training datasets. From a data perspective, the most intuitive solution is to synthesize data for rare poses. Specifically, the rule-based methods apply manual manipulations (such as Cutout and GridMask) to the existing data, so the limited diversity of the data constrains the model. An alternative method is to learn the underlying data distribution via deep generative models (such as ControlNet and HumanSD) and then sample “new data” from the distribution. This works …

Transforming Urban Dynamics: Harnessing Large Language Models For Smarter Mobility, Hao Xue, Ming Jin, Shirui Pan, Flora Salim, Guansong Pang

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) has the potential to analyze mobility data and make mobility systems smarter by leveraging diverse data sources such as geospatial data, transportation logs, and real-time sensor data to optimize traffic flow, enhance public transportation systems, and support the development of autonomous vehicles. With the newly emerged generative AI paradigm, exemplified by large language models (LLMs), there is great potential to transform the current AI applications in mobility, transportation, and urban domains. This article provides an overview of recent efforts and aims to shed light on the challenges and future opportunities to facilitate the adaptation of LLMs for …

Fedart: A Neural Model Integrating Federated Learning And Adaptive Resonance Theory, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed clients while preserving data privacy. However, prevailing FL approaches aggregate the clients’ local models into a global model through multi-round iterative parameter averaging. This leads to the undesirable bias of the aggregated model towards certain clients in the presence of heterogeneous data distributions among the clients. Moreover, such approaches are restricted to supervised classification tasks and do not support unsupervised clustering. To address these limitations, we propose a novel one-shot FL approach called Federated Adaptive Resonance Theory (FedART) which leverages self-organizing Adaptive Resonance Theory (ART) …

A Survey Of Multilingual Large Language Models, Libo Qin, Qiguang Chen, Yuhang Zhou, Zhi Chen, Yinghui Li, Lizi Liao, Min Li, Wanxiang Che, Philip S. Yu

Research Collection School Of Computing and Information Systems

Multilingual large language models (MLLMs) leverage advanced large language models to process and respond to queries across multiple languages, achieving significant success in polyglot tasks. Despite these breakthroughs, a comprehensive survey summarizing existing approaches and recent developments remains absent. To this end, this paper presents a unified and thorough review of the field, highlighting recent progress and emerging trends in MLLM research. The contributions of this paper are as follows. (1) Extensive survey: to our knowledge, this is the pioneering thorough review of multilingual alignment in MLLMs. (2) Unified taxonomy: we provide a unified framework to summarize the current progress …

Adversarial Generative Flow Network For Solving Vehicle Routing Problems, Ni Zhang, Jingfeng Yang, Zhiguang Cao, Xu Chi

Research Collection School Of Computing and Information Systems

Recent research into solving vehicle routing problems (VRPs) has gained significant traction, particularly through the application of deep (reinforcement) learning for end-to-end solution construction. However, many current construction-based neural solvers predominantly utilize Transformer architectures, which can face scalability challenges and struggle to produce diverse solutions. To address these limitations, we introduce a novel framework beyond Transformer-based approaches, i.e., Adversarial Generative Flow Networks (AGFN). This framework integrates the generative flow network (GFlowNet)-a probabilistic model inherently adept at generating diverse solutions (routes)-with a complementary model for discriminating (or evaluating) the solutions. These models are trained alternately in an adversarial manner to improve …

Double Oracle Neural Architecture Search For Game Theoretic Deep Learning Models, Aye Phyu Phyu Aung, Xinrun Wang, Ruiyu Wang, Hau Chan, Bo An, Xiaoli Li, J. Senthilnath

Research Collection School Of Computing and Information Systems

In this paper, we propose a new approach to train deep learning models using game theory concepts including Generative Adversarial Networks (GANs) and Adversarial Training (AT) where we deploy a double-oracle framework using best response oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. The same concept can be applied to AT with attacker and classifier as players. Training these models is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as training algorithms for both GAN and AT have a large-scale strategy space. Extending our …

Recdreamer: Consistent Text-To-3d Generation Via Uniform Score Distillation, Chenxi Zheng, Yihong Lin, Bangzhen Liu, Xuemiao Xu, Yongwei Nie, Shengfeng He

Research Collection School Of Computing and Information Systems

Current text-to-3D generation methods based on score distillation often suffer from geometric inconsistencies, leading to repeated patterns across different poses of 3D assets. This issue, known as the Multi-Face Janus problem, arises because existing methods struggle to maintain consistency across varying poses and are biased toward a canonical pose. While recent work has improved pose control and approximation, these efforts are still limited by this inherent bias, which skews the guidance during generation. To address this, we propose a solution called RecDreamer, which reshapes the underlying data distribution to achieve more consistent pose representation. The core idea behind our method …

The Effectiveness Of Local Updates For Decentralized Learning Under Data Heterogeneity, Tongle Wu, Zhize Li, Ying Sun

Research Collection School Of Computing and Information Systems

We revisit two fundamental decentralized optimization methods, Decentralized Gradient Tracking (DGT) and Decentralized Gradient Descent (DGD), with multiple local updates. We consider two settings and demonstrate that incorporating local update steps can reduce communication complexity. Specifically, for  $\mu$-strongly convex and $L$-smooth loss functions, we proved that local DGT  achieves communication complexity {}{$\tilde{\mathcal{O}} \Big(\frac{L}{\mu(K+1)} + \frac{\delta + {}{\mu}}{\mu (1 - \rho)} + \frac{\rho }{(1 - \rho)^2} \cdot \frac{L+ \delta}{\mu}\Big)$}, where $K$ is the number of additional local update}, $\rho$ measures the network connectivity and $\delta$ measures the second-order heterogeneity of the local losses. Our results reveal the tradeoff between communication and …

Uso De Herramientas De Inteligencia Artificial Generativa Por Parte De Docentes En Una Escuela Del Suroeste De Puerto Rico, Glorimar N. Rodríguez Guiliani

Theses and Dissertations

Esta disertación aplicada fue diseñada para investigar el nivel de conocimiento, uso y dificultades que enfrentan los docentes de quinto a duodécimo grado en una escuela privada del suroeste de Puerto Rico respecto a tecnologías emergentes las cuales presentan desafíos significativos para los docentes y los estudiantes. Se exploró la utilización de herramientas de inteligencia artificial generativa (GenAI) como ChatGPT dentro y fuera del aula para actividades pedagógicas y administrativas.

Los hallazgos revelaron una notable carencia en el conocimiento docente sobre el uso y habilidades de la inteligencia artificial. Se identificó, también, una deficiencia en la capacidad de los docentes …

Discovery Of Photosynthetic Oxic N2-Fixation In Cyanobacteria Using Wet Lab And Machine Learning Approaches, James A. Young Iii

Electronic Theses and Dissertations

No abstract provided.

Harnessing The Power Of Gradient-Based Simulations For Multi-Objective Optimization In Particle Accelerators, Kishansingh Rajput, Malachi Schram, Auralee Edelen, Jonathan Colen, Armen Kasparian, Ryan Roussel, Adam Carpenter, He Zhang, Jay Benesch

Data Science Faculty Publications

Particle accelerator operation requires simultaneous optimization of multiple objectives. Multi-objective optimization (MOO) is particularly challenging due to trade-offs between the objectives. Evolutionary algorithms, such as genetic algorithms (GAs), have been leveraged for many optimization problems, however, they do not apply to complex control problems by design. This paper demonstrates the power of differentiability for solving MOO problems in particle accelerators using a deep differentiable reinforcement learning (DDRL) algorithm. We compare the DDRL algorithm with model-free reinforcement learning (MFRL), GA, and Bayesian optimization (BO) for simultaneous optimization of heat load and trip rates in the continuous electron beam accelerator facility. The …

Fares On Fairness: Using A Total Error Framework To Examine The Role Of Measurement And Representation In Training Data On Model Fairness And Bias, Patrick Oliver Schenk, Christoph Kern, Trent D. Buskirk

Data Science Faculty Publications

Data-driven decisions, often based on predictions from machine learning (ML) models are becoming ubiquitous. For these decisions to be just, the underlying ML models must be fair, i.e., work equally well for all parts of the population such as groups defined by gender or age. What are the logical next steps if, however, a trained model is accurate but not fair? How can we guide the whole data pipeline such that we avoid training unfair models based on inadequate data, recognizing possible sources of unfairness early on? How can the concepts of data-based sources of unfairness that exist in the …

Prompt-Based Learning For Few-Shot Class-Incremental Learning, Jicheng Yuan, Hang Chen, Songsong Tian, Wenfa Li, Lusi Li, Enhao Ning, Yugui Zhang

Computer Science Faculty Publications

Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to incrementally learn new tasks from a limited number of labeled samples, while retaining knowledge of previously learned tasks, mimicking the way humans learn. In this paper, we introduce a novel approach called Prompt Learning for FSCIL (PL-FSCIL), which leverages the power of prompts alongside a pre-trained Vision Transformer (ViT) model to effectively tackle the challenges of FSCIL. Our approach explores the feasibility of directly applying visual prompts in FSCIL, using a simplified model architecture. PL-FSCIL integrates two key prompts: the Domain Prompt and the FSCIL Prompt. Both are tensors …

An Analytical Review Of Preprocessing Techniques In Bengali Natural Language Processing, Sovon Chakraborty, Protiva Das, Shakib Mahmud Dipto, Md Aktaruzzaman Pramanik, Jannatun Noor

Computer Science Faculty Publications

Research in Bengali Natural Language Processing (BNLP) is rapidly expanding. Despite being one of the most widely spoken languages in the world, BNLP research remains insufficient, particularly in Bengali speech recognition. The languages rich morphology, agglutinative structure, and diverse dialects make text and speech processing especially challenging. However, these challenges can be addressed with effective preprocessing techniques. Various organizations in Bangladesh and West Bengal are integrating Natural Language Processing (NLP) into their services, but without a thorough understanding of preprocessing, these implementations remain incomplete. Applying proper preprocessing techniques to the Bengali language will serve as a foundation for developing robust …

Can Llms Beat Humans On Discerning Human-Written And Llm-Generated Science News, Dominik Soós, Meng Jiang, Jian Wu

Computer Science Faculty Publications

Science news is increasingly important in connecting scientists and the public by sharing discoveries and innovations. With the rise of large language models (LLMs), there is potential to automate science news creation, but concerns exist about the quality of LLM-generated news versus human-written news. This paper explores whether LLMs can outperform humans in distinguishing between human-written and LLM-generated news. Inspired by the Chain-of-Thought prompting method, we designed a simple yet effective variant called Guided Few-shot (GFS), which encodes the characteristics of news of two types with examples. Our experiments indicated that GFS with just a single example effectively boosted the …

Deepssetracer 2.0: Improved Deep Learning Model Performance For Protein Secondary Structure Segmentation From Cryo-Em Maps, Bryan Hawickhorst, Thu Nguyen, Willy Wriggers, Jiangwen Sun, Jing He

Computer Science Faculty Publications

DeepSSETracer is a method for segmenting protein secondary structure from medium-resolution (5-10Å) cryogenic electron microscopy (cryo-EM) density maps. We conducted experiments and ablation studies to examine the effects of normalization methods, max-pooling, activation functions, and loss calculation region on DeepSSETracer. By combining multiple technical improvements, the performance of the new version, DeepSSETracer 2.0, was significantly enhanced compared to DeepSSETracer 1.1. On a set of 77 test cases, the weighted average per-voxel F1 score increased from 62.1% to 70.3% for helix detection, and from 47.8% to 62.5% for β-sheet detection. While each of the five modifications in the network enhanced the …

Benchmarking And Improving Foundation Model Dietary Estimates From Meal Images, Yongcheng Mu, Jiangwen Sun, Jing He

Computer Science Faculty Publications

Accurate quantifying dietary contents, such as calories, proteins, carbohydrates, and fats, from an image of a meal plate is vital for managing diabetes. Recently, Large Multimodal Models (LMMs) have excelled in complex vision-language tasks due to their use of very large, highly diverse data. This study benchmarked the use of seven LMMs that include full and lightweight models of GPT, Gemini, and Llama for nutrition estimation based on Google's Nutrition5k dataset and our own phone-collected DonateAndLearn dataset. We analyzed the performance of LMMs and the RGB-D fusion model, in which the RGB-D model was specifically trained using Nutrition5k data. On …