Artificial Intelligence and Robotics Commons^™

Cyberoception: Finding A Painlessly-Measurable New Sense In The Cyberworld Towards Emotion-Awareness In Computing, Tadashi Okoshi, Zexiong Gao, Yi Zhen Tan, Takumi Karasawa, Takeshi Miki, Wataru Sasaki, Rajesh Krishna Balan

Research Collection School Of Computing and Information Systems

In Affective computing, recognizing users’ emotions accurately is the basis of affective human–computer interaction. Understanding users’ interoception contributes to a better understanding of individually different emotional abilities, which is essential for achieving inter-individually accurate emotion estimation. However, existing interoception measurement methods, such as the heart rate discrimination task, have several limitations, including their dependence on a well-controlled laboratory environment and precision apparatus, making monitoring users’ interoception challenging. This study aims to determine other forms of data that can explain users’ interoceptive or similar states in their real-world lives and propose a novel hypothetical concept “cyberoception,” a new sense (1) which …

Hierarchical Frameworks For Scaling-Up Multi-Agent Coordination, Minghong Geng

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning has emerged as a powerful framework for developing collaborative behaviors in autonomous systems. However, existing MARL methods often struggle with scalability in terms of both the number of agents and decision-making horizons. My research focuses on developing hierarchicalapproaches to scale up MARL systems through two complementary directions: structural scaling by increasing the number of coordinated agents and temporal scaling by extending planning horizons. My initial work introduced HiSOMA, a hierarchical framework integrating self-organizing neural networks with MARL forlong-horizon planning, and MOSMAC, a benchmark for evaluating MARL methods on multi-objective MARL scenarios. Building on these foundations, my recent …

Mosmac: A Multi-Agent Reinforcement Learning Benchmark On Sequential Multi-Objective Tasks, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Recent advancements in multi-agent reinforcement learning (MARL) have demonstrated success on various cooperative multi-agent tasks. However, current benchmarks often fall short of representing realistic scenarios that demand agents to execute sequential tasks over long temporal horizons while balancing multiple objectives. To address this limitation, we introduce multi-objective SMAC (MOSMAC), a comprehensive MARL benchmark designed to evaluate MARL methods on tasks involving multiple objectives, sequential subtask assignments, and varying temporal horizons. MOSMAC requires agents to tackle a series of interconnected subtasks in StarCraft II while simultaneously optimizing for multiple objectives, including combat, safety, and navigation. Through rigorous evaluation of nine state-of-the-art …

Creating Talking Points For Client Advisers At Banks To Promote Sustainable Investing, Wewe Zi Yi, Pradeep Varakantham, Alan Megargel

Research Collection School Of Computing and Information Systems

Environmental, social and governance (ESG) factors have become key nonfinancial factors for investors to evaluate companies with respect to understanding material risks and growth opportunities. While not mandatory, companies are providing ESG reports that outline progress in different ESG metrics (six broad metrics and 15 specific ones). Client advisers (CAs) read these reports to identify key metrics of interest to investors. Given the number of companies and investment products, however, it is not feasible for CAs to read all the reports, which can sometimes run into tens or hundreds of pages). The authors have developed multiple frameworks building on leading …

Hello Again! Llm-Powered Personalized Agent For Long-Term Dialogue, Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus on brief single-session interactions, neglecting the real-world demands for long-term companionship and personalized interactions with chatbots. Crucial to addressing this real-world need are event summary and persona management, which enable reasoning for appropriate long-term dialogue responses. Recent progress in the human-like cognitive and reasoning capabilities of LLMs suggests that LLM-based agents could significantly enhance automated perception, decision-making, and problem-solving. In response to this potential, we introduce a model-agnostic framework, the Long-term Dialogue Agent (LD-Agent), which incorporates three independently …

Query Understanding In Llm-Based Conversational Information Seeking, Yifei Yuan, Zahra Abbasiantaeb, Yang Deng, Mohammad Aliannejadi

Research Collection School Of Computing and Information Systems

Query understanding in Conversational Information Seeking (CIS) involves accurately interpreting user intent through context-aware interactions. This includes resolving ambiguities, refining queries, and adapting to evolving information needs. Large Language Models (LLMs) enhance this process by interpreting nuanced language and adapting dynamically, improving the relevance and precision of search results in real-time. In this tutorial, we explore advanced techniques to enhance query understanding in LLM-based CIS systems. We delve into LLM-driven methods for developing robust evaluation metrics to assess query understanding quality in multiturn interactions, strategies for building more interactive systems, and applications like proactive query management and query reformulation. We …

Sans: Efficient Densest Subgraph Discovery Over Relational Graphs Without Materialization, Yudong Niu, Yuchen Li, Jiaxin Jiang, Laks V. S. Lakshmanan

Research Collection School Of Computing and Information Systems

How can we efficiently identify the densest subgraph over relational graphs? Existing dense subgraph discovery (DSD) approaches assume that a relational graph H is already derived from a heterogeneous data source and they focus on efficient discovery of the densest subgraph on the materialized H. Unfortunately, materializing relational graphs can be resource-intensive, which thus limits the practical usefulness of existing algorithms over large datasets. To mitigate this, we propose a novel Summary-bAsed deNsest Subgraph discovery (SANS) system. Our unique summary-based peeling algorithm forms the core of SANS. Following the peeling paradigm, it utilizes summaries of each node's neighborhood to efficiently …

Gamba: Marry Gaussian Splatting With Mamba For Single-View 3d Reconstruction, Qiuhong Shen, Zike Wu, Xuanyu Yi, Pan Zhou, Hanwang Zhang, Shuicheng Yan, Xinchao Wang

Research Collection School Of Computing and Information Systems

We tackle the challenge of efficiently reconstructing a 3D asset from a single image at millisecond speed. Existing methods for single-image 3D reconstruction are primarily based on Score Distillation Sampling (SDS) with Neural 3D representations. Despite promising results, these approaches encounter practical limitations due to lengthy optimizations and significant memory consumption. In this work, we introduce Gamba, an end-to-end 3D reconstruction model from a single-view image, emphasizing two main insights: (1) Efficient Backbone Design: introducing a Mamba-based GambaFormer network to model 3D Gaussian Splatting (3DGS) reconstruction as sequential prediction with linear scalability of token length, thereby accommodating a substantial number …

Hierarchical Learning-Based Graph Partition For Large-Scale Vehicle Routing Problems, Yuxin Pan, Ruohong Liu, Yize Chen, Zhiguang Cao, Fangzhen Lin

Research Collection School Of Computing and Information Systems

Neural solvers based on the divide-and-conquer approach for Vehicle Routing Problems (VRPs) in general, and capacitated VRP (CVRP) in particular, integrates the global partition of an instance with local constructions for each subproblem to enhance generalization. However, during the global partition phase, misclusterings within subgraphs have a tendency to progressively compound throughout the multi-step decoding process of the learning-based partition policy. This suboptimal behavior in the global partition phase, in turn, may lead to a dramatic deterioration in the performance of the overall decomposition-based system, despite using optimal local constructions. To address these challenges, we propose a versatile Hierarchical Learning-based …

Enhancing Sub-Optimal Trajectory Stitching: Spatial Composition Rvs For Offline Rl, Sheng Zang, Zhiguang Cao, Bo An, Senthilnath Jayavelu, Xiaoli Li

Research Collection School Of Computing and Information Systems

Reinforcement learning via supervised learning (RvS) has been known as a burgeoning paradigm for offline reinforcement learning (RL). While return-conditioned RvS (RvS-R) predominates across a wide range of datasets pertaining to the offline RL tasks, recent findings suggest that goal-conditioned RvS (RvS-G) outperforms in specific sub-optimal datasets where trajectory stitching is crucial for achieving optimal performance. However, the underlying reasons for this superiority remain insufficiently explored. In this paper, employing didactic experiments and theoretical analysis, we reveal that the proficiency of RvS-G in stitching trajectories arises from its adeptness in generalizing to unknown goals during evaluation. Building on this insight, …

Rotation-Adaptive Point Cloud Domain Generalization Via Intricate Orientation Learning, Bangzhen Liu, Chenxi Zheng, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Shengfeng He

Research Collection School Of Computing and Information Systems

The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ …

Shipnavisim: Data-Driven Simulation For Real-World Maritime Navigation, Quang Anh Pham, Janaka Chathuranga Brahmanage, Akshat Kumar

Research Collection School Of Computing and Information Systems

Maritime traffic management in busy ports faces growing challenges due to increased vessel traffic and complex waterway interactions. Strategies such as e-navigation by the International Maritime Organization aim to enhance navigation safety through traffic digitization. Maritime traffic simulation is essential for these systems, offering a virtual environment to model, analyze, and optimize traffic flows. Unlike road traffic, there are few simulators for maritime traffic, and they often lack realism and multi-ship interactions. In this paper, we (a) present ShipNaviSim, a data-driven maritime traffic simulator that utilizes a large-scale dataset over 2 years and electronic navigation charts to model vessel movements …

Worldcuisines: A Massive-Scale Benchmark For Multilingual And Multicultural Visual Question Answering On Global Cuisines, Genta Indra Winata, Et. Al

Research Collection School Of Computing and Information Systems

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside …

Unlocking The Planning Capabilities Of Llms Through Maximum Diversity Fine-Tuning, Wenjun Li, Changyu Chen, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have demonstrated impressive task-solving capabilities through prompting techniques and system designs, including solving planning tasks (e.g., math proofs, basic travel planning) when sufficient data is available online and used during pre-training. However, for planning tasks with limited prior data (e.g., blocks world, advanced travel planning), the performance of LLMs, including proprietary models like GPT and Gemini, is poor. This paper investigates the impact of fine-tuning on the planning capabilities of LLMs, revealing that LLMs can achieve strong performance in planning through substantial (tens of thousands of specific examples) fine-tuning. Yet, this process incurs high economic, time, …

Eduqate: Generating Adaptive Curricula Through Rmabs In Education Settings, Sidney Tio, Dexun Li, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

There has been significant interest in the development of personalized and adaptive educational tools that cater to a student's individual learning progress. A crucial aspect in developing such tools is in exploring how mastery can be achieved across a diverse yet related range of content in an efficient manner. While Reinforcement Learning and Multi-armed Bandits have shown promise in educational settings, existing works often assume the independence of learning content, neglecting the prevalent interdependencies between such content. In response, we introduce Education Network Restless Multi-armed Bandits (EdNetRMABs), utilizing a network to represent the relationships between interdependent arms. Subsequently, we propose …

Towards Multimodal Empathetic Response Generation: A Rich Text-Speech-Vision Avatar-Based Benchmark, Han Zhang, Zixiang Meng, Meng Luo, Hong Han, Lizi Liao, Erik Cambria, Hao Fei

Research Collection School Of Computing and Information Systems

Empathetic Response Generation (ERG) is one of the key tasks of the affective computing area, which aims to produce emotionally nuanced and compassionate responses to user's queries. However, existing ERG research is predominantly confined to the singleton text modality, limiting its effectiveness since human emotions are inherently conveyed through multiple modalities. To combat this, we introduce an avatar-based Multimodal ERG (MERG) task, entailing rich text, speech, and facial vision information. We first present a large-scale high-quality benchmark dataset, AvaMERG, which extends traditional text ERG by incorporating authentic human speech audio and dynamic talking-face avatar videos, encompassing a diverse range of …

On Learning Informative Trajectory Embeddings For Imitation, Classification And Regression, Zichang Ge, Changyu Chen, Arunesh Sinha, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

In real-world sequential decision making tasks like autonomousdriving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification,and clustering. For example, self-driving cars must replicate humandriving behaviors, while robots and healthcare systems benefitfrom modeling decision sequences, whether or not they come fromexpert data. Existing trajectory encoding methods often focus onspecific tasks or rely on reward signals, limiting their ability togeneralize across domains and tasks.Inspired by the success of embedding models like CLIP andBERT in static domains, we propose a novel method for embeddingstate-action trajectories into a latent space that captures the skillsand competencies in the …

Artificial Intelligence In Orthopedic Medical Education: A Comprehensive Review Of Emerging Technologies And Their Applications, Kyle Sporn, Rahul Kumar, Phani Paladugu, Tejas Sekhar, Swapna Vaja, Tamer Hage, Ethan Waisberg, Chirag Gowda, Ram Jagadeesan, Nasif Zaman, Alireza Tavakkoli

SKMC Student Presentations and Publications

Integrating artificial intelligence (AI) and mixed reality (MR) into orthopedic education has transformed learning. This review examines AI-powered platforms like Microsoft HoloLens, Apple Vision Pro, and HTC Vive Pro, which enhance anatomical visualization, surgical simulation, and clinical decision-making. These technologies improve the spatial understanding of musculoskeletal structures, refine procedural skills with haptic feedback, and personalize learning through AI-driven adaptive algorithms. Generative AI tools like ChatGPT further support knowledge retention and provide evidence-based insights on orthopedic topics. AI-enabled platforms and generative AI tools help address challenges in standardizing orthopedic education. However, we still face many barriers that relate to standardizing data, …

Improving Image Quality In Electrical Capacitance Tomography Using Otsu Thresholding, Josiah Nombo

Tanzania Journal of Engineering and Technology (TJET)

Electrical Capacitance Tomography (ECT) is an imaging technique used in industrial process monitoring, particularly for monitoring and measuring the composition of multiphase flows. Despite its widespread application, the commonly used Linear Back Projection (LBP) algorithm often produces low-quality images due to its limited ability to handle high permittivity contrasts and nonlinearities. This study investigates the use of Otsu thresholding as a post-processing technique to enhance ECT image quality. By maximizing inter-class variance in the image histogram, Otsu thresholding improves contrast, clarity, and structural definition, enabling more effective segmentation of oil and gas components in multiphase flows. The proposed Otsu-based reconstruction …

Artificial Intelligence Applications For Grid-Connected Solar Inverters, Utkirjon Ubaydullaev, Sarvinoz Mirzaeva, Hasan Mustafoev

Chemical Technology, Control and Management

The increasing global demand for renewable energy has highlighted the importance of grid-connected solar inverters in ensuring efficient and stable power conversion. However, challenges such as fluctuations in solar energy generation, grid disturbances, and power quality issues necessitate advanced control strategies. The integration of artificial intelligence (AI) into solar inverters presents a transformative solution, enhancing performance, adaptability, and reliability in real-world applications.

This review explores the role of AI techniques, including machine learning (ML), deep learning (DL), fuzzy logic, and reinforcement learning (RL), in optimizing key inverter functionalities such as maximum power point tracking (MPPT), fault detection, power quality enhancement, …

Development Of A Microcontroller-Based Intelligent Traffic Light Control System For Vehicular Movement In T-Junctions, Frederick O. Ehiagwina

Tanzania Journal of Engineering and Technology (TJET)

This research is devoted to the issue of regulating traffic congestion in major cities using light-dependent resistors coupled with the PIC16F877A microcontroller. This study proposes an intelligent traffic control system for T-Junctions, utilizing sensing and control to optimize traffic flow through dynamic phase adjustments and congestion reduction, enabled by a microcontroller-based decision-making system. The proposed system reduces traffic congestion, automates control, and enhances safety, minimizing accidents and lowering infrastructure costs. Under simulated environment, it demonstrates an average response time of 50 ms and achieves 99% accuracy in displaying the correct countdown. Finally, the number of state transitions handled per minute …

Design And Performance Analysis Of Fiber Bragg Grating Temperature Sensor For Industrial Processes Sensing Applications, Paul Stone Stone Brown Macheso S.B.

Tanzania Journal of Engineering and Technology (TJET)

The Fiber Bragg Grating (FBG) sensor has become a widespread sensing device because of its small size, passive design, immunity to electromagnetic interference, and direct ability to measure physical properties like temperature and strain. Recently, femtosecond infrared laser processing and regeneration techniques have resulted in the development of stable high-temperature gratings, which are a powerful tool in smart factories, an aspect of the fourth Industrial Revolution (4IR), and show promise for application in harsh environments like high pressure, high temperature, or ionizing radiation. The development of stable high-temperature gratings that can withstand harsh environmental factors like high temperatures, pressures, and …

Application Of Artificial Neural Network Models For Predicting Diesel And Petrol Prices In The Geographically Sparsed Regions In Tanzania, John M. Kafuku

Tanzania Journal of Engineering and Technology (TJET)

Fuel consumption in Tanzania, mainly diesel and petrol, accounts for 82 percent of the energy consumption in the country, with significant price volatility affecting market stability, availability of fuel, and investment decisions. This study uses an artificial neural network (ANN) with a backpropagating algorithm to predict fuel prices in four regions of Tanzania. Key input parameters include the currency inflation rate (CIR), the petrol fuel inventory (PFI), the diesel fuel inventory (DFI), and the fuel transport costs (FTC). The study selected the 6-10-10-2 ANN structures for Sumbawanga-Rukwa, Mpanda-Katavi, and Mbeya-Mbeya as well as 6-10-9-2 for the Songea-Ruvuma region. The results …

A Fuzzy Based Framework For Sustainable Technology Selection In Small-Scale Gold Mining Operations, John M. Kafuku

Tanzania Journal of Engineering and Technology (TJET)

Small-scale gold mining (SSGM) operations in Tanzania has been operating inefficiently due to inadequate mining processing technologies, poor working tools, lack of enough capital, and insufficient electricity. Despite the efforts made by different stakeholders in boosting the sustainability of SSGM yet the sector has not reached the expected goal. This paper proposes a framework for appropriate technology selection to help small scale gold miners in evaluating various gold mineral processing technologies. The framework utilizes the fuzzy logic set theory for technology evaluation and selection. The developed framework for technology selection upon validation provided results that technology adequacy of more than …

Synthetic Inertia Provision For Load Frequency Control In Networks With High Penetration Of Renewable Energy Sources, Paulina Mkoi

Tanzania Journal of Engineering and Technology (TJET)

The integration of renewable energy sources (RESs) such as solar photovoltaic (PV) and wind energy has become a promising solution as the world shifts toward clean energy. Solar PV and wind resources are increasingly replacing conventional synchronous generators, leading to reduced system inertia and increased vulnerability to frequency instability during disturbances. To address this challenge, this study proposes a novel synthetic inertia provision strategy using a battery energy storage system (BESS) integrated alongside solar PV. The proposed method dynamically compensates for the loss of inertia by considering the variability of solar PV output due to changes in irradiance and temperature. …

Generating More Equitable Fair Use, Jacqueline Kessel

Pepperdine Law Review

From advancing healthcare and education to threatening democratic systems, generative artificial intelligence (AI) has demonstrated a capacity to positively and negatively impact society. And these benefits and consequences are not shared equitably. Copyright law, however, stands as a powerful mechanism in monitoring AI system development. Several complaints have charged generative AI system developers with copyright infringement, alleging that (1) ingesting copyrighted works as training data infringes the copyright owner’s exclusive right to reproduce works in copies and (2) generating AI outputs infringes the exclusive right to prepare derivative works because the outputs are based upon the works on which the …

Analysis And Monitoring Of A Robotics Curriculum: Are Simnow Modules Valuable?, Jacob Applegarth, Ibrahim Baida, Anthony Iacco, Ngan Nguyen, Nathan Novotny

Posters

No abstract provided.

Exploring The Impacts Of An Adaptive Haptic Heartbeat Within A Socially Assistive Robot, Jade Thompson

Honors Theses

This research investigates the therapeutic effects of an adaptive haptic heartbeat within Therabot, a stuffed robotic dog. A simulated haptic heartbeat that adjusts its own speed based on user heart rate was developed for integration within Therabot. A user study evaluated the effects of various heartbeat behaviors on user experiences with Therabot, with respect to improvements in self-reported state anxiety, physiological improvements, and perceptions of the robot. A relationship was found between improvements in self-reported state anxiety and positive opinions of Therabot, regardless of condition. Additionally, differences were found between conditions with respect to improved aspects of state anxiety, with …

Autonomous Intelligence In Fashion: A Comprehensive Analysis Of Agentic Ai Across The Fashion Ecosystem, Andrew Burnstine

Faculty and Staff Publications & Presentations

The fashion industry is undergoing a paradigm shift with the emergence of agentic artificial intelligence (AI), a sophisticated class of intelligent systems exhibiting autonomous decision-making, continuous learning, and adaptive action with minimal human intervention. Moving beyond traditional AI applications in fashion focused on predictive analytics, generative tools, and supervised automation, agentic AI introduces a transformative paradigm wherein intelligent agents proactively navigate the complexities inherent in design, manufacturing, supply chain optimization, and consumer personalization. This paper presents a comprehensive exploration of the evolving role of agentic AI across the multifaceted fashion ecosystem, offering an in-depth analysis of its technological underpinnings, operational …

The Attitudes And Perspectives Of Laboratory Professionals On The Use Of Machine Learning Combined With Maldi For Viral Identification: A Qualitative Study, Grace Johnson

Honors Projects

The use of matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) with machine learning (ML) has been proposed by numerous studies as a novel approach for viral identification. However, the development and implementation of this instrumentation is still in its early stages, and laboratory professionals' perspectives on its feasibility, accuracy, implementation, and effect on current laboratory operating procedures remain underexplored.

This study aimed to investigate laboratory professionals’ attitudes and opinions regarding the use of MALDI-TOF-MS coupled with machine learning for viral identification, focusing on perceived benefits, barriers, and factors that would affect participants’ opinions on implementation.

A qualitative descriptive research …