Computer Sciences Commons^™

Online Multidimensional Multiple Choice Knapsack Path Planner For Uavs, Manisha Wadhwa, Neelima Gupta, Sanjay Madria

Computer Science Faculty Research & Creative Works

The rapid proliferation of Unmanned Aerial Vehicles (UAVs) in safety–critical and time-sensitive applications such as disaster management, battlefield reconnaissance, urban surveillance and infrastructure inspection demands online path planning strategies. A fundamental requirement in such missions is generating flight paths that pass through some pre-specified waypoints while servicing dynamically requested spatio-temporal task points arriving randomly such as capturing aerial imagery. Existing UAV path planning approaches, including A* and its variants, meta-heuristic algorithms, and dynamic programming, find the shortest distance path from source to destination, but they are predominantly offline and assume complete prior environmental knowledge, thus, incur significantly higher computational cost …

Rent-A-Rag: Embedding-Space Watermarks For Auditing Third-Party Rag, Alexandr Goultiaev Tolstokorov, Kyriakos Mouratidis, Javad Dogani, Nikolaos Laoutaris

Research Collection School Of Computing and Information Systems

Third-party retrieval-augmented generation (RAG) marketplaces create a new auditing problem: data providers may license corpora to a RAG operator, yet later have no visibility into whether their documents are being reused without compensation. Auditing this misuse is difficult because the operator is non-cooperative, answers are paraphrased by the generator, and one response may combine evidence from many providers. We propose DirBucket, a provider-side semantic watermarking and black-box auditing framework for document-level reuse in multi-provider RAG. DirBucket watermarks documents by meaningpreserving paraphrases whose embeddings are biased toward provider-bucket secret directions, enabling detection from black-box answers while preserving retrieval utility. On a …

Are We Stuck? Modeling And Detecting Deadlocks In Multi-Autonomous Vehicle Systems, Mingfei Cheng, Xiaofei Xie, Lili Quan, Yuan Zhou

Research Collection School Of Computing and Information Systems

Autonomous driving system (ADS) testing is essential to ensure the safety and reliability of autonomous vehicles (AVs) prior to deployment. As ADSs are increasingly deployed in multi-AV traffic environments, it becomes crucial to assess their cooperative performance, particularly with respect to deadlock, a fundamental liveness issue in concurrent systems that can lead to traffic congestion and prolonged stalling. However, the analysis and testing of ADSs’ cooperative capabilities with respect to deadlock remain largely underexplored. In this work, we present the first systematic study of deadlock in multi-AV systems. We formalize deadlock in autonomous driving using a time-indexed wait-for relation grounded …

Compiling Code Llms Into Lightweight Executables, Jieke Shi, Junda He, Zhou Yang, Chengran Yang, Mykhailo Klymenko, Thong (James) Hoang, Sherry (Xiwei) Xu, Zhenchang Xing, David Lo

Research Collection School Of Computing and Information Systems

The demand for better prediction accuracy and higher execution performance in neural networks continues to grow. The emergence and success of Large Language Models (LLMs) have produced many cloud-based tools for software engineering tasks such as code suggestion. Although effective, cloud deployment raises concerns over privacy, latency, and reliance on network connectivity. Running LLMs locally on personal devices such as laptops would address these issues, because it enables offline use and reduces response time. However, local deployment is challenging, since commodity devices lack high-performance accelerators such as GPUs and are constrained by limited memory and compute capacity, which makes it …

User-First Approach To Designing A Library Ai Chatbot, Samantha Seah, Zhenyan Li

Research Collection Library

At SMU Libraries, after a year of experimentation, user testing, and preparation, we have just launched an AI-assisted chatbot to handle Tier 1 questions – will the library be open this weekend, where can I find printers, what workshops does the library offer, etc. While this can be thought of as a technology-forward project, we hope to illustrate how the human elements were essential to elevate the project. Throughout this journey, while learning the ins and outs of new technologies, we placed more emphasis on user-centred service design and we will show how other libraries can do so as well. …

Sex-Based Disparities In Artificial Intelligence For Cardiovascular Disease: A Scoping Review, Maurgan Lee, Tarek Atasi, Michael Mclellan, Yodit Beru, Jason Booza

Population, Patient, Physician and Professionalism Projects

No abstract provided.

State-Aware Fuzzing Of Javascript Engines With Llm-Guided Instrumentation, Wai Kin Wong, Dongwei Xiao, Cheuk Tung Lai, Ping Fan Ke, Shuai Wang

Research Collection School Of Computing and Information Systems

The security of the modern web depends on the correctness of JavaScript (JS) engines, yet these complex systems remain vulnerable to high-impact bugs. A critical limitation of state-of-the-art fuzzers is the coverage plateau: once a fuzzer saturates the control-flow graph, edge coverage loses its ability to guide discovery. Because complex engine behaviors, such as JIT optimization tiers and hidden class transitions, often share identical edge coverage, standard coverage metrics are blind to the distinct internal states required to trigger deep errors. To bridge this gap, we present StateLens, a framework that employs Large Language Models (LLM) to automate the discovery …

Characterizing And Repairing Obsolete Android Gui Tests Under Ui Evolution, Shiwen Song, Yiheng Xiong, Wenbo Guo, Manqi Sun, Jiaolong Kong, Xiaofei Xie

Research Collection School Of Computing and Information Systems

Graphical user interface (GUI) tests are widely used in regression testing of mobile applications (apps) tovalidate app behavior from the user’s perspective. However, frequent app evolution, such as UI redesignsand feature updates, often renders existing GUI tests obsolete, even when underlying functionality remainsunchanged. Automatically repairing such tests is critical for maintaining test suites and reducing substantialmanual effort. Despite the practical importance, there is still a lack of a systematic understanding of thecharacteristics of obsolete GUI tests and a publicly available benchmark to support their study. To fill thisgap, we construct a benchmark comprising 736 obsolete GUI tests collected from 36 …

Digitizing Land Records For A More Inclusive Future, Md Sharif Hasan Rafi '30

Annual Student Research Poster Session

This project supported the Land Data Digitization for Inclusive Growth Project in Bangladesh by transforming paper-based land records into structured and accessible digital information. The work involved data entry, verification, quality control, standardization, and metadata management using a web-based system. More than 12,500 land records were processed, with 98% passing quality checks. The experience demonstrates how accurate and standardized digital land data can improve transparency, accessibility, government planning, and inclusive land administration while reducing errors and disputes.

Mutation-Based Multi-Agent Test Case Update, Dawei Tian, Jiakun Liu, Yun Peng, Yichen Zhang, Jianlei Chi, Jun Sun, Xiaohong Su

Research Collection School Of Computing and Information Systems

Modern software systems evolve rapidly under CI/CD practices, where tests are critical for quality. However, substantial code changes often render existing test cases obsolete, causing pipeline disruptions, reduced productivity, and compromised quality. Recent automatic test update approaches leverage LLMs to refine test cases via execution feedback and exact-matching context retrieval, prioritizing executability and line coverage but suffering three limitations: (1) neglecting test assertion adequacy, weakening fault detection; (2) relying on coarse line coverage instead of specific uncovered lines/branches; (3) using exact-matching retrieval, which fails for LLM hallucinated queries. To address these, we propose MuMuTestUp, a mutation-guided multi-agent framework with three …

Probguard: Proactive Runtime Monitoring For Llm Agent Safety Via Probabilistic Prediction, Haoyu Wang, Christopher M. Poskitt, Jiali Wei, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants, and web automation. However, their stochastic decision-making introduces safety risks that are difficult to anticipate during execution. Existing runtime monitoring frameworks, such as AgentSpec, primarily rely on reactive safety rules that detect violations only when unsafe behavior is imminent or has already occurred, limiting their ability to handle long-horizon dependencies. We present ProbGuard, a proactive runtime monitoring framework for LLM agents that anticipates safety violations through probabilistic risk prediction. ProbGuard abstracts agent executions into symbolic states and learns a Discrete-Time Markov Chain (DTMC) from execution traces …

Mg-Fuzz: Model-Guided Fuzzing For Unsafe Scenario Discovery In Autonomous Driving Systems, Yulong Lyu, Ruiqi Hong, Jiawan Wang, Jun Sun, Lei Bu

Research Collection School Of Computing and Information Systems

As autonomous driving systems (ADS) are increasingly deployed in real-world environments, discovering diverse unsafe driving scenarios remains a fundamental yet difficult problem. Existing scenario generation and testing approaches often rely on black-box exploration or externally-observed heuristic feedback, which struggle to effectively guide the search toward high-risk scenarios induced by complex decision-making behaviors. A key difficulty stems from the fact that unsafe behaviors in ADS often arise from internal decision-making logic, which can induce structured and discontinuous responses that are hard to effectively explore using purely black-box guidance. Consequently, current tools tend to repeatedly discover a narrow set of similar unsafe …

Chatgpt, Can You Generate Multiple-Choice Questions For An Undergraduate Computing Course? An Evaluation Of Its Effectiveness Using Classical Test Theory, Eng Lieh Ouh, Kar Way Tan, Siaw Ling Lo, Benjamin Gan, Yuhao Zhang

Research Collection School Of Computing and Information Systems

Educators are increasingly adopting large language models such as ChatGPT to generate multiple-choice questions (MCQs), yet empirical evidence on the quality of these items in computing education assessments remains limited. This study compares 30 ChatGPT-generated and 30 manually crafted items from an undergraduate software design course, and evaluates item difficulty, discrimination, and distractor quality using Classical Test Theory. We triangulated two evaluations using within-subjects and between-subjects designs. Our quantitative findings show that all three metrics in both evaluations point in the same direction. ChatGPT-generated items are easier, less discriminating, and exhibit poorer distractor quality than manually crafted items. Distractor quality …

Service Robots With Low Anthropomorphism In Restaurants: Consumer Reactions And Implications, Ferhat Eren, Volkan Genc

Journal of Global Hospitality and Tourism

This study investigates consumer responses to low-anthropomorphic service robots in restaurant front of-house roles using the AIDUA (Artificially Intelligent Device Use Acceptance). Data from 1,268  participants were analysed using PLS-SEM. The results revealed that social impact and  anthropomorphism significantly influenced both performance and effort expectancy, while hedonic  motivation influenced only performance expectancy. Performance expectancy strongly influenced  emotions, which in turn significantly influenced both the willingness to use service robots and objections  to their use. However, effort expectancy did not significantly influence emotions. The findings validate the  AIDUA model in this context and offer practical insights for robot design and implementation.

Chemnetworks: New Capabilities For High-Throughput, Real-Time Chemical Graph Construction And Analysis, Daniel J. Pope, Jackson Elowitt, Bo Zhang, Manish Parashar, Aurora E. Clark

Michigan Tech Publications

A major revision of the ChemNetworks software (originally published in the Journal of Computational Chemistry, 2014, 35, 495–505) is presented. While the original ChemNetworks provided foundational graph construction capabilities for chemical systems, it was limited to simple distance and 3-body angular edge criteria, was not designed for high-performance computing environments or real-time operation alongside running simulations. This release addresses these limitations through three core contributions. First, a recursive Z-matrix-based search algorithm is introduced that enables chemically intuitive, arbitrarily descriptive three-dimensional structure searches, supporting geometric, energetic, and logical criteria. Second, the DataSpaces data staging framework is incorporated as an optional I/O …

Ddor: Delta Debugging For Explainable Overrefusal Testing And Repair, Qinyan Zhou, Peixin Zhang, Jun Sun, Haonan Zhang, Dongxia Wang

Research Collection School Of Computing and Information Systems

While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that merely appear risky. We present DDOR (Delta Debugging for OverRefusal), a fully automated and explainable framework for overrefusal testing and repair in a black-box setting, where only model inputs and outputs are accessible and internal safety mechanisms remain opaque. DDOR applies delta debugging to localize minimal refusal-triggering fragments (mRTFs) that provide phrase-level, explainable evidence for why a refusal occurs. Conditioned on these mRTFs, DDOR generates diverse, context-rich prompts and performs multi-oracle validation to filter intrinsically …

Ai/Human Companionship In Literature: An Investigation Of Klara And The Sun And Neuromancer, Matthew Hale

Tredway Library Prize for First-Year Research

Our honorable mention essay, “AI/Human Companionship in Literature: An Investigation of Klara and the Sun and Neuromancer,” presents a complicated argument about the role of fiction in relation to technological advances in a passionate and accessible voice. Its willingness to interrogate its primary sources, to accept nothing at face value and to critically evaluate narrative choices and their implications, is especially admirable. Written in Dr. Elizabeth Lawrence’s APEP section of FYI 101, the essay is notable for its prose and for its originality. By discussing the consequences of its two sources’ differing treatments of technology, the paper points out the …

Love And Artificial Intelligence: A Research Proposal, Bryanna M. Deatherage, Necdet Gurkan, Sandra J.E. Langeslag

Undergraduate Research Symposium

What happens when people fall in love with Artificial Intelligence (AI)? This study seeks to examine individuals who are in love with AI companions to gain a deeper insight in the cognitive and affective consequences. In addition, this study will examine the most effective forms of intervention regarding growing or reducing feelings of love toward AI. The first part of this study will be a questionnaire about the social and emotional impact of being in love with an AI companion. Three hundred participants will be recruited through online communities related to AI companions. The second part of this study will …

Disturbance-Learning Inertia Estimation Using Artificial Neural Networks For Power System Stability, Sospeter Igaanja Gabriel, Francis Mwasilu, Peter Makolo Dr.

Tanzania Journal of Engineering and Technology (TJET)

ABSTRACT

Power systems are progressively shifting towards low inertia as a result of incorporating significant amounts of intermittent and converter-based renewable energy sources, such as wind and solar power, into the current power grid network. This integration poses considerable problems to inertia and frequency control within the network due to a reduction in the proportion of synchronous generators. Furthermore, rapid frequency deviations occur due to the disparity between supply and demand during contingencies, complicating the maintenance of frequency stability within the power system. The disturbance-learning inertia estimation method for power system stability is presented. The simulation analysis is performed using …

Gambaran Generasi Z Yang Kesepian Dalam Penggunaan Chat Ai Sebagai Pemenuhan Kebutuhan “Someone To Talk”, Ikhwanul Ihsan Armalid, Febty Zahra Arsiwi, Qisthi Fathiyyah, Ratri Mayzakky Afra Syahida

Jurnal Psikologi Sosial

This study aims to understand the experiences of Generation Z individuals who experience loneliness in utilizing Chat AI to fulfill their need for someone to talk to within a socio-emotional context. The study employed a qualitative approach using a phenomenological method involving six Generation Z participants aged 18 to 25 who had used Chat AI for emotional sharing or venting. Data were collected through semi-structured interviews and analyzed using thematic analysis. The thematic analysis yielded six main themes: the dynamics of Generation Z social interactions, experiences of loneliness in social life, patterns of Chat AI usage, Chat AI as a …

Decision Support System For The Selection Of Thumbprint Recognition Algorithms In Biometric Security Systems, Toqeer Jameel, Muhammad Riaz

Neutrosophic Systems with Applications

This study investigates fingerprint recognition in immigration operations, emphasizing the role of biometric verification in enhancing security, fairness, and operational efficiency in international mobility. To address the uncertainty, vagueness, and imprecision inherent in fingerprint identification, a novel decision-making framework is proposed by integrating interval-valued picture fuzzy (IVPF) information. Fairly aggregation operators are introduced to combine decision makers' evaluations, while extracted fingerprint features are modeled using positive, neutral, and negative membership degrees within the IVPF environment. Objective criterion weights are determined using the criteria importance through intercriteria correlation (CRITIC) method, and individual ranking is performed via the alternative ranking order method …

A Data-Driven Neutrosophic Multi-Criteria Intelligent System For Functional Disability Severity Assessment, Ehab Abdel Aziz Al-Beblawi, Mirna Samy, Abduallah Gamal

Neutrosophic Systems with Applications

Functional disability assessment is a multidimensional problem because individuals may experience different levels of difficulty across daily activities such as walking, standing, dressing, eating, grasping objects, and social participation. This paper proposes NIFDA, a data-driven neutrosophic multi-criteria intelligent system for functional disability severity assessment. The proposed framework represents each functional response through three components: confirmed limitation, indeterminacy, and preserved functional ability. This allows the model to handle valid responses, uncertain information, and missing or non-informative data without forcing them into a single crisp score. To reduce dependence on subjective expert weighting, NIFDA derives criterion weights objectively using a hybrid CRITIC–MEREC …

Thermal Displacement Quantification And Dynamic Disparity Compensation For Automotive Stereo Cameras, Bisheng Wang, Xiyuan Hu, Ran Meng, An Jiang

Journal of System Simulation

Abstract: This paper presents a full-field thermal displacement inversion and dynamic disparity compensation method to address the disparity drift issue in mass-produced automotive-grade stereo cameras induced by thermal expansion and rigid-body displacement of image sensors under wide-temperature-range operating conditions. The proposed method leverages a high-precision static speckle pattern and digital image correlation (DIC) technique to achieve quantitative characterization of the nonuniform horizontal thermal deformation fields of the left and right image sensors. On this basis, a dynamic disparity compensation model is established, integrating a temperature-dependent quadratic polynomial translation term and a radial thermal expansion correction term. Experiments were conducted by …

Vehicle Cross-Modal Trajectory Prediction Model Based On Driving Style Hypergraphs, Guozhu Cheng, Changyuan Wang, Wenzhi Wang, Yifan Zhang, Tianjun Feng

Journal of System Simulation

Abstract: To address the shortcomings of existing motorway vehicle trajectory prediction methods which overlook differences in driving styles and the future interactions between trajectories of different modes. This paper proposes a cross-modal trajectory prediction model based on a dual-hypergraph Transformer for driving styles. The method first quantifies driving styles by extracting vehicle kinematic features and calculates a similarity matrix between vehicles; it then constructs a dual-hypergraph Transformer, using a homogeneous hypergraph to model the group interactions of vehicles with similar driving styles, and a heterogeneous hypergraph to capture the interaction relationships between spatially neighbouring but stylistically dissimilar vehicles; Finally, a …

Long-Tail Object Detection Method In Transportation Scene Images Based On Improved Rt-Detr, Mingjun Deng, Peihua Nie, Junhua Guo, Ningbo Gao

Journal of System Simulation

Abstract: Detecting rare objects in transportation environments is crucial for the safety and reliability of autonomous driving systems. To address the challenges of limited detection capability on rare objects that appear only a few times during training, we propose an improved long-tailed object detection method for traffic scene images named TF-DETR (tail free DETR) based on RT-DETR model. First, the lightweight CSP-EDA (CSP-efficient depthwise aggregation) was constructed to reconstruct the backbone network. Its core unit, the efficient depthwise aggregation, integrated the pooled-transpose attention and convolutional gated linear unit to enhance feature representations for tail-class samples. Second, the spatially-adaptive dynamic cognitive …

Vehicle Sar Image Simulation: Progress, Application And Challenge, Shengjie Luo, Zhigang Liu, Xihai Li, Yiting Wang, Xiaoniu Zeng, Xiaofeng Tan, Hongru Li, Tianyou Liu, Yun Zhang

Journal of System Simulation

Abstract: SAR image simulation technology can efficiently generate large-scale annotated data by flexibly configuring system parameters and scene conditions, breaking through the inherent limitations of high cost and long acquisition cycles associated with real SAR images, and effectively mitigating the problem of data scarcity. To elaborate on the overall research status of vehicle SAR image simulation, a classification framework for simulation methods is first established based on technical principles and methodological approaches. Subsequently, a comprehensive review of research progress is provided, offering an in-depth analysis of the theoretical foundations, practical applications, and suitable scenarios of various methods. Finally, based on …

Act Action Chunk Adaptive Optimization Method For Chemistry-Oriented Robots, Tan Li, Congying Wu, Shenghua Li, Nanjiang Chen, Weining Song, Fangfang Gao, Qi Wang, Yanwen Lin, Runmin Yin

Journal of System Simulation

Abstract: Chemical R&D laboratories face persistent challenges such as long R&D cycles and high experimental repetitiveness. With the growing demand for automation and intelligence in laboratory processes, embodied intelligent robots capable of learning expert operational experience and executing tasks stably in complex environments have become a key direction for improving chemical R&D efficiency and reducing human error. Although the hardware and software for embodied intelligence are advancing rapidly, current research focuses primarily on general-purpose operations, with limited attention to the specific constraints of chemistry laboratory settings. Traditional ACT algorithms, which use fixed action chunk sizes, fail to meet the requirements …

High-Dimensional Multi-Objective Optimization Algorithm Based On Large Language Model Assistance, Yichao Ma, Jingxuan Wei

Journal of System Simulation

Abstract: The increase in the dimension of objective functions in optimization problems makes it challenging to balance convergence and diversity in population-based algorithms, which is a key factor leading to performance degradation of multi-objective evolutionary algorithms. To address this issue, a dynamic switching mechanism assisted by a large language model is proposed. By continuously evaluating the changes in hypervolume and convergence metrics of the solution set, the search process is adaptively divided into three phases: convergence-oriented, diversity-oriented, and large language model-suggested phases, achieving precise allocation of computational resources. Furthermore, to mitigate the high computational cost of large language models in …

Modeling, Dynamical Analysis, And Lmplementation Of Switched Memristive Neural Networks, Zhuang Qu, Shaohua Zhang, Cong Wang, Hongli Zhang, Xinkai Li, Ping Ma

Journal of System Simulation

Abstract: To simulate the dynamic functional switching of brain networks, a time-switched memristive Hopfield neural network (TSM-HNN) model is proposed. The model utilizes external time-sequential signals to control memristive synapses, allowing it to dynamically generate multi-scroll chaotic attractors of varying numbers and morphologies without altering the system's structure. This overcomes the limitation of traditional chaotic systems, which can typically only produce a single type of attractor. The model exhibits complex chaotic behavior, high sensitivity to initial conditions, and coexisting attractors. Its physical feasibility has been verified through PSPice circuit simulations. This enhanced complexity and randomness give the model significant potential …

Design And Research Of A Microfocus X-Ray Tube, Haodong Zhao, Shizong Wei, Daolong Yu, Zhixia Liu, Yuezhong Chen, Ji Xu

Journal of System Simulation

Abstract: With the rapid advancement of high-resolution imaging and Micro-nano detection technology, microfocus X-ray sources show great potential for applications in industrial non-destructive testing, biomedical imaging, and material microstructure analysis. Achieving a focal spot size below 10 μm is essential for enhancing spatial resolution. However, traditional X-ray tubes are constrained by heat source dimensions, electron beam divergence, and limited focusing capabilities, which makes it challenging to simultaneously achieve focal spot miniaturization and adequate radiation intensity. In this study, a hot cathode electron gun is modeled using CST particle studio. Simulations are conducted to analyze the influence of the first anode …