Artificial Intelligence and Robotics Commons^™

Rethinking Teaching Evaluation Reports: Designing Ai-Transformed Student Feedback For Instructor Engagement, Ruoxi Shang, Keri Mallari, Au Wei Bin Yeong, Ken Yasuhara, Anthony Tang, Gary Hsieh

Research Collection School Of Computing and Information Systems

Student feedback is critical for improving teaching, yet instructors often avoid reading evaluations due to emotional burden and information overload. We present a systematic exploration of how language models can distill and transform student evaluations into adaptive, actionable insights. Through a systematic design space exploration combining 4 feedback strategies (removing harmful content, paraphrasing criticism, sandwiching negatives, adding constructive suggestions) with 4 presentation formats (themes, cards, letters, chatbots), we created six AI-augmented prototypes of teaching evaluations. Interviews with 16 post-secondary instructors revealed that effective use of AI in feedback processing should: (1) support action formation through focused views and divergent thinking, …

Polymind: Parallel Visual Diagramming With Large Language Models To Support Prewriting Through Microtasks, Qian Wan, Jiannan Li, Huanchen Wang, Zhicong Lu

Research Collection School Of Computing and Information Systems

Prewriting is the process of generating and organising ideas before a first draft. It consists of a combination of informal, iterative, and semi-structured strategies such as visual diagramming, which poses a challenge for collaborating with large language models (LLMs) in a turn-taking conversational manner. We present Polymind, a visual diagramming tool that leverages multiple LLM-powered agents to support prewriting. The system features a parallel collaboration workflow in place of the turn-taking conversational interactions. It defines multiple ''microtasks'' to simulate group collaboration scenarios such as collaborative writing and group brainstorming. Instead of repetitively prompting a chatbot for various purposes, Polymind enables …

Information Provision And Search Frictions: Evidence From The Taxi Industry In Singapore, Sumit Agarwal, Shih-Fen Cheng, Jussi Keppo, Long Wang, Yang Yang

Research Collection School Of Computing and Information Systems

Search frictions and misallocation are common in decentralized transportation markets. Using novel trip-level data of taxis in Singapore, this paper examines the impactof real-time demand information at airport terminals on search frictions. The information reduces taxi supply misallocation, increasing deadheading speed by 16.3% and decreasing deadheading time by 10.77%, benefiting both passengers and drivers. It raises daily earnings by $3.70 USD and adds 6.2 minutes of operational time per airport-trip taxi. Spatial spillovers are primarily observed among drivers in adjacentdistricts. Taxis from the Budget Terminal and drivers with fewer prior airport pickups benefit more from this information.

Filterfl: Knowledge Filtering-Based Data-Free Backdoor Defense For Federated Learning, Yanxin Yang, Ming Hu, Xiaofei Xie, Yue Cao, Pengyu Zhang, Yihao Huang, Mingsong Chen

Research Collection School Of Computing and Information Systems

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is vulnerable to poisoning attacks, especially backdoor attacks. By using poisoned data for local training or directly changing the model parameters, attackers can easily inject backdoors into the model, which can trigger the model to make misclassification of targeted patterns in images. To address these issues, we propose a novel data-free trigger-generation-based defense approach based on the two characteristics of backdoor attacks: i) triggers are learned …

Stable Score Distillation, Haiming Zhu, Yangyang Xu, Chenshu Xu, Tingrui Shen, Wenxi Liu, Yong Du, Jun Yu, Shengfeng He

Research Collection School Of Computing and Information Systems

Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing strength. These limitations stem from reliance on complex auxiliary structures, which introduce conflicting optimization signals and restrict precise, localized edits. We introduce Stable Score Distillation (SSD), a streamlined framework that enhances stability and alignment in the editing process by anchoring a single classifier to the source prompt. Specifically, SSD utilizes Classifier-Free Guidance (CFG) equation to achieve cross-prompt alignment, and introduces a constant term null-text branch to stabilize the optimization process. This approach preserves the original content's …

Stroke2sketch: Harnessing Stroke Attributes For Training-Free Sketch Generation, Rui Yang, Huining Li, Yiyi Long, Xiaojun Wu, Shengfeng He

Research Collection School Of Computing and Information Systems

Generating sketches guided by reference styles requires precise transfer of stroke attributes, such as line thickness, deformation, and texture sparsity, while preserving semantic structure and content fidelity. To this end, we propose Stroke2Sketch, a novel training-free framework that introduces cross-image stroke attention, a mechanism embedded within self-attention layers to establish fine-grained semantic correspondences and enable accurate stroke attribute transfer. This allows our method to adaptively integrate reference stroke characteristics into content images while maintaining structural integrity. Additionally, we develop adaptive contrast enhancement and semanticfocused attention to reinforce content preservation and foreground emphasis. Stroke2Sketch effectively synthesizes stylistically faithful sketches that closely …

Seeing 3d Through 2d Lenses: 3d Few-Shot Class-Incremental Learning Via Cross-Modal Geometric Rectification, Tuo Xiang, Xuemiao Xu, Bangzhen Liu, Jinyi Li, Yong Li, Shengfeng He

Research Collection School Of Computing and Information Systems

The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and texture bias. While recent approaches integrate 3D data with 2D foundation models (e.g., CLIP), they suffer from semantic blurring caused by texture-biased projections and indiscriminate fusion of geometric-textural cues, leading to unstable decision prototypes and catastrophic forgetting. To address these issues, we propose Cross-Modal Geometric Rectification (CMGR), a framework that enhances 3D geometric fidelity by leveraging CLIP’s hierarchical spatial semantics. Specifically, we introduce a Structure-Aware Geometric Rectification module that hierarchically …

Omnivton: Training-Free Universal Virtual Try-On, Zhaotong Yang, Yuhui Li, Shengfeng He, Xinzhe Li, Yangyang Xu, Junyu Dong, Yong Du

Research Collection School Of Computing and Information Systems

Image-based Virtual Try-On (VTON) techniques rely on either supervised in-shop approaches, which ensure high fidelity but struggle with cross-domain generalization, or unsupervised in-the-wild methods, which improve adaptability but remain constrained by data biases and limited universality. A unified, training-free solution that works across both scenarios remains an open challenge. We propose OmniVTON, the first training-free universal VTON framework that decouples garment and pose conditioning to achieve both texture fidelity and pose consistency across diverse settings. To preserve garment details, we introduce a garment prior generation mechanism that aligns clothing with the body, followed by continuous boundary stitching technique to achieve …

Cross-Subject Mind Decoding From Inaccurate Representations, Yangyang Xu, Bangzhen Liu, Wenqi Shao, Yong Du, Shengfeng He, Tingting Zhu

Research Collection School Of Computing and Information Systems

Decoding stimulus images from fMRI signals has advanced with pre-trained generative models. However, existing methods struggle with cross-subject mappings due to cognitive variability and subject-specific differences. This challenge arises from sequential errors, where unidirectional mappings generate partially inaccurate representations that, when fed into diffusion models, accumulate errors and degrade reconstruction fidelity. To address this, we propose the Bidirectional Autoencoder Intertwining framework for accurate decoded representation prediction. Our approach unifies multiple subjects through a Subject Bias Modulation Module while leveraging bidirectional mapping to better capture data distributions for precise representation prediction. To further enhance fidelity when decoding representations into stimulus images, …

Fcad: Feature-Coupled Anisotropic Diffusion For Continuous Graph Learning, Amitoz Azad, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

In this work, we propose a novel continuous graph neural network called FCAD (Feature-Coupled Anisotropic Diffusion) for the task of node classification on graphs. Our approach is motivated by the success of feature-coupled anisotropic diffusion PDEs in multivalued image restoration. Our method introduces a total variation regularization-inspired anisotropic term to control diffusion between nodes and incorporates a learnable parameterization for feature coupling during the diffusion process. Our model performs competitively against several GNN baselines for both heterophilous and homophilous graphs, demonstrating notable benefits for heterophilous graphs due to the learnable feature coupling.

Parameter-Efficient Variational Autoencoder For Multimodal Multi-Interest Recommendation, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning user preferences in recommendation systems is enriched by multimodal features, such as textual and visual content, and amplified by multi-interest modeling with Variational AutoEncoders (VAEs). However, prior efforts are limited by single modality focus and cumbersome, parameter-heavy architecture designs. To address these limitations, we introduce an innovative solution that blends the semantic richness of multimodal data with the representational power of multi-representation VAEs. Drawing inspiration from Mixture of Experts (MoE), we cast each VAE as an expert tailored to a specific modality, then fuse them via a novel parameter-merging function into a lean, unified model. This approach efficiently captures …

Search Trajectory Network-Enhanced Multi-Objective Dynamic Algorithm Configuration, Robbert Reijnen, Zaharah Bukhsh, Hoong Chuin Lau, Yaoxin Wu, Yingqian Zhang

Research Collection School Of Computing and Information Systems

Deep reinforcement learning (DRL) has emerged as an effective technique for dynamic algorithm configuration, particularly in evolutionary computation, enabling adaptive parameter updates during algorithmic execution. DRL-based methods have shown broad applicability across different problem domains and are designed to configure algorithms without problem-specific information, making them highly transferable across problem variants and scalable to different problem sizes. This paper proposes a novel graph neural network-based approach that learns representations of Search Trajectory Networks (STNs) to track the convergence behavior of multiple objectives and dynamically reconfigures multiobjective evolutionary algorithms during execution. By capturing how solutions evolve and interact over time, the …

Memad: Structured Memory Of Debates For Enhanced Multi-Agent Reasoning, Shuai Ling, Lizi Liao, Dongmei Jiang, Weili Guan

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) demonstrate remarkable in-context learning capabilities but often struggle with complex, multi-step reasoning. Multi-Agent Debate (MAD) frameworks partially address these limitations by enabling iterative agent interactions. However, they neglect valuable historical insights by treating each new debate independently. In this paper, we propose Memory-Augmented MAD (MeMAD), a parameter-free memory-augmented MAD framework that systematically organizes and reuses past debate transcripts. MeMAD stores structured representations of successful and unsuccessful reasoning attempts enriched with self-reflections and peer feedback. It systematically retrieves them via semantic similarity at inference time to inform new reasoning tasks. Our experiments on challenging mathematical reasoning, scientific …

Optimizing Cybersecurity Through Ai Predictive Analytics And Human Expertise, Cathy Mae C. Dutong

Journal of the Symposium of University Research and Creative Expression

Project Mentor(s): Hideki Takei, DBA

As cybersecurity threats evolve in complexity and scale, the reliance on artificial intelligence (AI) has become increasingly prevalent across both public and private sectors. This study examines the dual role of AI-driven predictive analytics in strengthening organizational cybersecurity, while addressing the ongoing need for human oversight. Through a mixed-method approach, combining survey data from cybersecurity professionals with an extensive literature review, this research analyzes AI's capacity to detect emerging threats, the systemic challenges associated with AI integration, and the indispensable role of human expertise in interpreting AI outputs. Findings indicate that while AI enhances proactive …

Global Trends In Ai-Driven Product Development: A Cross-Country Analysis, Shilpa Dhananjayan

Journal of the Symposium of University Research and Creative Expression

Project Mentor(s): Hideki Takei, DBA

Artificial Intelligence (AI) is transforming industries and accelerating global innovation, yet its benefits remain unevenly distributed. A nation’s AI readiness—its capacity to adopt and implement AI technologies—plays a crucial role in economic growth and technological advancement. Key determinants of AI readiness include digital infrastructure, data accessibility, government policies, research and development (R&D) investment, and workforce development. This study examines the relationship between AI readiness, AI adoption, innovation, R&D investment of a nation, Digital Infrastructure Index (DII) and Human Capital Index (HCI) using a Random Forest regression model. Findings reveal a strong correlation between AI adoption …

A Feature Engineering Technique For Enhancing The Generalization Of Machine Learning Models In Estimating Crop Evapotranspiration, Gaku Yokoyama, Sohta Harigai, Shigehiro Kubota, Koichi Nomura, Gregory R. Goldsmith, Daisuke Yasutake, Tomoyoshi Hirota, Masaharu Kitano

Biology, Chemistry, and Environmental Sciences Faculty Articles and Research

Accurate and precise estimation of evapotranspiration (ET) is crucial for understanding the terrestrial carbon, water, and energy cycles. While process-based models of ET, such as the Penman–Monteith model offer robust generalization capabilities, they are limited by the need for detailed parameters (e.g., stomatal conductance,) that are challenging to measure continuously. On the other hand, machine learning models can estimate ET by capturing relationships between ET and environmental variables without experimentally measuring model parameters. However, machine learning models face the challenge of limited generalizability. This issue is particularly significant given the uncertainty introduced by changing climatic …

Ai Exposure And The Future Of Work: Linking Task-Based Measures To U.S. Occupational Employment Projections, Erik Vasilauskas, Michael Horrigan

Reports

No abstract provided.

Solution Of Fractional Order Diffusion Equations With Clique Neural Network, Merve Zeynep Kaya, Mesut Karabacak, Ercan Çelik

Mathematical Modelling and Numerical Simulation with Applications

In this paper, the clique artificial neural network method is used to solve the fractional diffusion equation, which is a subclass of partial differential equations. The clique neural network architecture is constructed using input, hidden, and output layers. Several degrees of clique polynomials were used as activation functions, and the output layer was obtained by multiplying them with weight coefficients. Subsequently, the optimization equation was derived, and the exact solution, numerical solution, and error function graphs were obtained using a specialized algorithm. Analysis of the results demonstrates that the clique artificial neural network method provides quicker and more accurate results …

Synergistic Modeling Of Hydrogel Gelation Via Time-Delay Dynamics And Machine Learning Algorithms, Mine Babaoglu, Dipesh ., Pankaj Kumar, Jagjit Singh Dhatterwal, Mansoor Alsulami

Mathematical Modelling and Numerical Simulation with Applications

This paper presents an integrated framework in which delay differential equation (DDE) modeling and machine learning (ML) approaches are coupled to study hydrogel formation kinetics, with emphasis on delayed crosslinker addition. Conventional mechanistic models disclose many physical and kinetic complexities of reacting mixtures; they seldom depict the nonlinear and time-evolving complexities inherent in developing polymer networks. To address this, a mathematical model is developed that examines how the insertion of crosslinkers affects system stability and equilibrium. Analytical and numerical results show that delays nearing critical levels cause bifurcation behavior with substantial implications on gelation kinetics. Sophisticated machine learning systems, including …

Non-Invasive Detection Of Choroidal Melanoma Via Tear-Derived Protein Corona On Gold Nanoparticles: A Machine Learning Approach, Hakimeh Rakhshandeh, Ahmad Nasiraei, Hamid Riazi-Esfahani, Babak Masoomian, Fariba Ghassemi, Mojtaba Arjmand, Saeed Heidari Keshel, Fatemeh Atyabi, Rassoul Dinarvand

Wills Eye Hospital Papers

This study investigates the feasibility of using tear sample analysis, based on protein corona formation on gold nanoparticles combined with electrospray ionization mass spectrometry (ESI-MS) and machine learning techniques, as a non-invasive approach for the detection of choroidal melanoma. The aim is to assess whether protein-nanoparticle interactions can support early and reliable identification of this ocular condition. Tear samples were collected using Schirmer strips from six healthy individuals and six patients diagnosed with choroidal melanoma, with subsequent augmentation to 18 samples per group. Gold nanoparticles (AuNPs, ~ 20 nm) were synthesized via citrate reduction and incubated with tear samples to …

Heuristic Weight Initialization For Transfer Learning In Classification Problems, Musulmon Lolaev, Anand Paul, Jeonghong Kim

School of Public Health Faculty Publications

Transfer learning is the predominant method for adapting pre-trained models on another task to new domains while preserving their internal architectures and augmenting them with requisite layers in Deep Neural Network models. Training intricate pre-trained models on a sizable dataset requires significant resources to fine-tune hyperparameters carefully. Most existing initialization methods mainly focus on gradient flow-related problems, such as gradient vanishing or exploding, or other existing approaches that require extra models that do not consider our setting, which is more practical. To address these problems, we suggest employing gradient-free heuristic methods to initialize the weights of the final new-added fully …

Retracted: Idea Density And Grammatical Complexity As Neurocognitive Markers, Diego Iacono, Gloria Feltis

Department of Neurology Faculty Papers

Language, a uniquely human cognitive faculty, is fundamentally characterized by its capacity for complex thoughts and structured expressions. This review examines two critical measures of linguistic performance: idea density (ID) and grammatical complexity (GC). ID quantifies the richness of information conveyed per unit of language, reflecting semantic efficiency and conceptual processing. GC, conversely, measures the structural sophistication of syntax, indicative of hierarchical organization and rule-based operations. We explore the neurobiological underpinnings of these measures, identifying key brain regions and white matter pathways involved in their generation and comprehension. This includes linking ID to a distributed network of semantic hubs, like …

Optimization Of Multi-Target Interception Scheme Based On Performance Simulation Modeling, Hanwen Liu, Zhimin Zhuo, Xue Yang

Journal of System Simulation

Abstract: The air attack scenarios faced by air defense weapons and equipment show the trend of saturation, diversification and intelligence. It is very important to establish multi-target interception efficiency model and optimize interception scheme according to simulation. The current intercepting efficiency index mainly considers the whole operation process, and can not guide the optimization of the intercepting scheme of specific intercepting rounds. The generation of interception schemes mainly relies on experience and simple mathematical model, which is difficult to cope with the increasingly complex and changeable battlefield environment. Therefore, an interception scheme advantage index that comprehensively considers interception probability and …

Design And Prediction Of Deep Fuzzy Neural Network, Chengbiao Wei, Taoyan Zhao, Jiangtao Cao, Ping Li

Journal of System Simulation

Abstract: A deep fuzzy neural network (DFNN) is proposed to solve the problem that the deep neural network has poor interpretability and the correction of the model is not targeted when dealing with the big data regression prediction problem. The proposed deep fuzzy neural network adopts an adaptive fuzzy Cmeans (AFCM) clustering algorithm in structural learning. The structure of the model, namely the number of rules and the antecedent parameters of the rules, is determined by calculating the introduced validity function. The identification of consequent parameters uses an improved grey wolf optimization (IGWO) algorithm. By replacing the linear decreasing strategy …

Kill Chain Efficiency Evaluation Model Based On Gray Dematel-Anp, Zejing Zhao, Junliang Shang, Yanpei Qin

Journal of System Simulation

Abstract: In modern conflict scenarios, the kill chain is integral to the comprehensive understanding, orchestration, and execution of military operations. Accurately appraising the efficiency of the kill chain is imperative for gaining insights into battle dynamics and strategically distributing military assets. However, traditional assessments of kill chain efficacy have been hampered by fragmented and isolated indicators that frequently overlook the interplay and influence among various segments of the kill chain. To address these limitations, based on the characteristics of each phase of the kill chain and the OODA loop theory, a new set of performance evaluation indices has been proposed. …

Optimization Method For Multi Agricultural Machinery Collaborative Operation Based On Genetic Algorithm And A* Algorithm, Yiran Yu, Huicheng Lai, Guxue Gao, Guo Zhang, Wangyinan Peng, Longfei Yang, Junhao Huang

Journal of System Simulation

Abstract: To address the uneven task distribution among multiple agricultural machines (referred to as farm machinery) and the high time cost due to numerous turning points at intersections, this paper proposes a task planning method that combines a pre-heat multi grouped genetic algorithm (PHMGA) with the turn A* algorithm (tA*). PHMGA allocates tasks to each piece of farm machinery based on the known environment, ensuring balanced workload through a cost objective function that considers travel, operation, and turning distances. It also designs various operators and strategies to search for nearoptimal solutions. The tA* algorithm is used to select paths …

Research On The Truth, Function And Common Principles Of Simulation, Haohua Xu, Bin Xiao, Yunhao Cui

Journal of System Simulation

Abstract: Simulation applications are becoming increasingly widespread and have a greater impact, while the theoretical foundation of simulation is relatively weak. This article provides a new definition of simulation by analyzing the common activities of simulation, which can include both virtual and real simulation forms; referring to Popper's three worlds theory, this paper discusses the objective authenticity of simulation from a philosophical perspective; From a methodological perspective, this paper elaborates on the methodological characteristics of simulation as an indirect cognitive object, revealing its significance in integrating human-machine intelligence and promoting knowledge evolution. It also discusses the common principles of simulation, …

A Model Combining Self-Attention And Weight Sharing For Human Activity Recognition, Lun Ma, Yue Yang, Daihe Wang, Guisheng Liao, Xing Li

Journal of System Simulation

Abstract: With the prevalence of wearable devices, human activity recognition based on wearable sensor data has garnered significant attention. The central issue in this field is how to extract effective behavioral information from raw sensor data to form corresponding feature vectors. Currently, convolutional neural networks and recurrent neural networks have been widely utilized for feature extraction from multisensory data. However, these networks struggle to globally capture the crucial temporal features inherent of human activity over time. To address this, a multi-CNN-BiLSTM-self attention (Multi-CBSA) model based on self-attention and weight sharing has been proposed, taking into consideration the logical correlations among …

Wingtip Docking Control Of Composite Aircraft Based On Adrc Theory, Chunlei Xie, Hongxia Hu, Weibo Han

Journal of System Simulation

Abstract: The process of wingtip docking in composite aircraft is challenged by significant unsteady vortex aerodynamic disturbances arising from the close-range coupling of wingtips, thereby posing considerable constraints on docking precision and flight safety. This study endeavors to address the intricate task of airborne wingtip docking control amidst wingtip vortex disturbances through a comprehensive investigation of airborne wingtip docking control technology, grounded in the tenets of active disturbance rejection control (ADRC) theory. Initially, a mathematical model encapsulating the dynamics of three-channel attitude/displacement during the docking operation, incorporating both the wingtip docking mechanism and the wingtip vortex model, is established. …

Solving The Vehicle Routing Problem Based On Deep Reinforcement Learning, Ming Jiang, Tao He

Journal of System Simulation

Abstract: The capacitated vehicle routing problem (CVRP) is a well-known combinatorial optimization challenge recognized as NP-hard due to its significant complexity. Building upon existing research, this paper introduces a novel end-to-end deep reinforcement learning approach based on a multi-pointer Transformer to tackle the CVRP. The proposed algorithm employs an invertible residual network in the encoder to encode input features, effectively reducing memory consumption. In the decoder, a multipointer network determines the probability distribution of solutions. To further enhance the performance of CVRP solutions, the algorithm leverages the symmetry in combinatorial optimization by implementing multi-trajectory parallel processing during both training …