Artificial Intelligence and Robotics Commons^™

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 …

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 …

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 …

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 …

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) …

Flexible Hybrid Self-Powered Piezo-Triboelectric Nanogenerator Based On Bto-Pvdf/Pdms Nanocomposites For Human Machine Interaction, Wentao Dong, Mengyun Li, Chang Chen, Kun Xie, Jinhua Hong, Lin Yang

Civil & Environmental Engineering Faculty Publications

As flexible and wearable electronics play more and more important role in smart watches, smart glass and virtual reality, and the power supply to the wearable electronics have been revealed more attentions for long-term usage and continuous healthy monitoring. To overcome the challenge, flexible self-powered BTO-PVDF/PDMS piezoelectric-triboelectric electric hybrid generators (BPP-HNG) are developed to human gesture monitoring and human machine interaction (HMI) application without external power supply. BPP-HNG based on BTO-PVDF and PDMS films are prepared by sol-gel and spin-coating method. When the BTO content is 20 wt.%, BPP-HNG exhibits better electrical performance with an output voltage of 20.51 V. …

Large Scale Machine Learning Over Knowledge Graphs, Bedirhan Gergin

Electronic Theses & Dissertations (2024 - present)

Knowledge graphs (KGs) have become popular across various fields, providing convenient access to web-based knowledge while storing and formalizing domain-specific information. By analyzing KGs, patterns, connections, and dependencies can be identified across different data sources, enabling the inference of new knowledge from given facts. As the use of KGs expands, the size of modern KGs has grown significantly, making them impossible to process within the main memory of a single computer. Distributed computing offers a viable solution to this challenge by leveraging the combined capabilities of multiple servers within a cluster. This thesis explores how distributed computing can be effectively …

Improving Generalizability In Image Manipulation Detection, Zhenfei Zhang

Electronic Theses & Dissertations (2024 - present)

Image manipulation detection (IMD) aims to determine whether an image has been tampered with and to identify the manipulated regions. These capabilities have become increasingly important with the rapid advancement of media editing and generation technologies, such as Photoshop and generative AI methods, which underscore the need for robust tools for media authentication. Although current state-of-the-art (SoTA) methods achieve strong results on common manipulation types, such as splicing, copy-move, and removal, they often struggle to generalize to manipulation types not represented in the training data. Consequently, their real-world applicability remains limited, with performance degrading significantly in practical scenarios.

In this …

Genai’S Impact On Global It Management: A Multi-Expert Perspective And Research Agenda, Yogesh K. Dwivedi, Laurie Hughes, Mohammad S. Al-Ahmadi, Vincent Dutot, Syed Q. Ahmed, Shahriar Akter, Rahul De’, Keyao Li, Nitish Singh, Paul Walton

Research outputs 2022 to 2026

Generative AI (GenAI) is disrupting global IT management and challenging established practice. The increasing use of GenAI technology is redefining localization, transforming existing workforce roles, outsourcing strategy, and team dynamics. Simultaneously, GenAI’s security complexities have prompted the rethinking of existing risk frameworks to meet a new set of challenges from GenAI enhanced cyber threats. This article explores these complex and converging factors, providing a roadmap to address GenAI’s significant impact on global IT management. We advocate the responsible adoption of GenAI and importance of building resilient, value-driven, globally consistent IT ecosystems able to adapt to the significant challenges and opportunities …

Panoscu: A Simulation-Based Dataset For Panoramic Indoor Scene Understanding, Mariia Khan, Yue Qiu, Yuren Cong, Jumana Abu-Khalaf, David Suter, Bodo Rosenhahn

Research outputs 2022 to 2026

Panoramic images offer a comprehensive spatial view that is crucial for indoor robotics tasks such as visual room rearrangement, where an agent must restore objects to their original positions or states. Unlike existing 2D scene change understanding datasets, which rely on single-view images, panoramic views capture richer spatial context, object relationships, and occlusions—making them better suited for embodied artificial intelligence (AI) applications. To address this, we introduce Panoramic Scene Change Understanding (PanoSCU), a dataset specifically designed to enhance the visual object rearrangement task. Our dataset comprises 5,300 panoramas generated in an embodied simulator, encompassing 48 common indoor object classes. PanoSCU …

On-Device Recommender Systems: A Comprehensive Survey, Hongzhi Yin, Liang Qu, Tong Chen, Wei Yuan, Ruiqi Zheng, Jing Long, Xin Xia, Yuhui Shi, Chengqi Zhang

Research outputs 2022 to 2026

Recommender systems have been widely deployed in various real-world applications to help users identify content of interest from massive amounts of information. Traditional recommender systems work by collecting user-item interaction data in a cloud-based data center and training a centralized model to perform the recommendation service. However, such cloud-based recommender systems (CloudRSs) inevitably suffer from excessive resource consumption, response latency, as well as privacy and security risks concerning both data and models. Recently, driven by the advances in storage, communication, and computation capabilities of edge devices, there has been a shift of focus from CloudRSs to on-device recommender systems (DeviceRSs), …

Fuel Consumption Prediction Using Bayesian Neural Networks, Syarifah Diana Permai, Jurike V. Moniaga, Zener Sukra Lie, Ferry Jie

Research outputs 2022 to 2026

Transportation is one of the necessities of life. Because humans need transportation to move from one location to another. Transportation requires fuel. On the other hand, fuel consumption is important and must be controlled. This is because fuel can come from both renewable and non-renewable energy sources, depending on the type and process of its formation. Several factors influence the fuel efficiency of a car, including the type of engine, vehicle weight, aerodynamics, driving habits, and other vehicle conditions. This research aims to predict car fuel consumption and identify the factors that affect fuel consumption. Several Machine Learning and Statistical …

Pfedrag: A Personalized Federated Retrieval-Augmented Generation System With Depth-Adaptive Tiered Embedding Tuning, Hangyu He, Xin Yuan, Kai Wu, Ren Ping Liu, Wei Ni

Research outputs 2022 to 2026

Large Language Models (LLMs) can undergo hallucinations in specialized domains, and standard Retrieval-Augmented Generation (RAG) often falters due to general-purpose embeddings ill-suited for domain-specific terminology. Though domain-specific fine-tuning enhances retrieval, centralizing data introduces privacy risks. The use of federated learning (FL) can alleviate this to some extent, but faces challenges of data heterogeneity, poor personalization, and expensive training data generation. We propose pFedRAG, a novel Personalized Federated RAG framework, which enables efficient collaborative fine-tuning of embedding models to address these challenges. The key contribution is a new Depth-Adaptive Tiered Embedding (DATE) architecture, which comprises a Global Shared Layer, combined using …

Implementing A Chatbot To Promote Hereditary Breast & Ovarian Cancer Genetic Screening In Women's Health: Identifying Barriers And Facilitators To Screening Adoption, Easton N. Wollney, Shireen Madani Sims, Luisel J. Ricks-Santi, Elizabeth Eddy, Daniel Wiesman, Carla L. Fisher

Department of Biomedical and Translational Sciences Faculty Publications

Background

To promote genetic screening among women at risk for hereditary breast and ovarian cancer (HBOC), the American College of Obstetricians and Gynecologists recommends that risk assessment be integrated into practice. Chatbots like the Genetic Information Assistant (Gia®) are increasingly implemented to expand access to hereditary genetic screening. Factors that impact chatbot implementation for HBOC risk screening and women's uptake are not fully realized. To refine implementation strategies prior to full scale implementation, we sought to identify women's perceived facilitators/barriers to adopting Gia screening in a rural population within a large healthcare system in the southern United States.

Methods

We …