Artificial Intelligence and Robotics Commons^™

Obstructive Sleep Apnea Prediction: A Comprehensive Review And Comparative Study, Thi Khanh Chi Huynh, Amonae Dabbs-Brown, Anna Jurek-Loughrey, James Mulhall, Tuan Dung Pham, Ngoc Phu Doan, Viet Hung Tran, Zichi Zhang, Xuan Hoang Nguyen, Yimeng An, Peixin Li, Phi Hung Nguyen, Thi Linh Hoang, Xinming Shi, Hans Vandierendonck, Sebastien Bailly, Jean-Louis Pépin, Thai Son Mai

Research Collection School Of Computing and Information Systems

Obstructive Sleep Apnea (OSA) is a highly prevalent sleep disorder linked to considerable public health burdens and comorbidities. However, its heterogeneous presentation and the limited accessibility of traditional diagnostic tools such as polysomnography (PSG) lead to widespread underdiagnosis. As a result, artificial intelligence (AI) approaches, including machine learning (ML) and deep learning (DL) models, have attracted attention as an alternative pathway to detection. This paper first provides a comprehensive review of AI-driven OSA diagnosis, covering different diagnosis problems, input-data types, data biases, pre-processing techniques, and model performance. We then leverage the largest clinical dataset used in OSA prediction to date, …

The Gains Do Not Make Up For The Losses: A Comprehensive Evaluation For Safety Alignment Of Large Language Models Via Machine Unlearning, Weixiang Zhao, Yulin Hu, Xingyu Sui, Zhuojun Li, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che

Research Collection School Of Computing and Information Systems

Machine Unlearning (MU) has emerged as a promising technique for aligning large language models (LLMs) with safety requirements to steer them forgetting specific harmful contents. Despite the significant progress in previous studies, we argue that the current evaluation criteria, which solely focus on safety evaluation, are actually impractical and biased, leading to concerns about the true effectiveness of MU techniques. To address this, we propose to comprehensively evaluate LLMs after MU from three aspects: safety, over-safety, and general utility. Specifically, a novel benchmark MuBench with 18 related datasets is first constructed, where the safety is measured with both vanilla harmful …

Evaluation Of Large Language Models As Decision Support Tools For Head And Neck Cancer Management: A Blinded Multidisciplinary Simulation Study, Sholem Hack, Ron J. Karni, Antonino Maniaci, Christopher E. Fundakowski, Luca Castellani, Fabiola Incandela, Remo Accorona, Miguel Mayo-Yanez, Martina Violati, Lorenzo Giannini, Niccolo' Mevio, Alberto Maria Saibene

Department of Otolaryngology - Head and Neck Surgery Faculty Papers

BACKGROUND: The management of head and neck cancer relies on multidisciplinary expertise; however, access to tumor boards remains variable. Large language models (LLMs) may support guideline-based decision-making, although performance in complex oncologic scenarios is not well defined.

METHODS: Fourteen synthetic cases based on real tumor board encounters were evaluated. Five blinded comparator arms produced recommendations: a human expert, Non-RAG-GPT-4, Non-RAG-GPT-5, RAG-GPT-4, and RAG-GPT-5. Eight head and neck oncologic surgeons scored each recommendation for appropriateness, clarity, specificity, and feasibility using 5-point Likert scales. Paired permutation testing and inter-rater reliability were assessed.

RESULTS: LLM outputs showed close alignment with expert recommendations. RAG-based …

Use Of Electrocardiograms To Identify Coronary Artery Disease: Cross-Validation Of An Artificial Intelligence Model, Michael Leasure, Indu Poornima, Adam Butchy, Utkars Jain, Devin Vasoya, Michael Warnick, Brent Williams, John Rehder, Prahlad Menon, Veronica A. Covalesky, Gary S. Mintz

Department of Medicine Faculty Papers

BACKGROUND: The current gold standard for the diagnosis of coronary artery disease (CAD) is invasive angiography; however, it is an invasive procedure. Therefore, we developed an artificial intelligence model designed to predict significant CAD from a resting digital 12-lead electrocardiogram (ECG).

OBJECTIVES: This retrospective study assessed the model's ability to predict clinically significant CAD in a patient population presenting for coronary angiography.

METHODS: From 2019 to 2021, 16,476 patients had a resting 12-lead digital ECG recorded within 90 days prior to coronary angiography. The artificial intelligence model was developed using 10-fold cross-validation methodology. Clinically significant disease was defined as angiographic …

A High-Resolution Daily Precipitation Fusion Framework Integrating Radar, Satellite, And Nwp Data Using Machine Learning Over South Korea, Hyoju Park, Hiroyuki Miyazaki, Menas Kafatos, Seung Hee Kim, Yangwon Lee

Institute for ECHO Articles and Research

Accurate precipitation mapping is essential for effective disaster management; however, individual radar, satellite, and numerical weather prediction products often struggle in the topographically complex terrain of South Korea. This study proposes a high-resolution (~500 m) daily precipitation fusion framework that integrates Korea Meteorological Administration (KMA) radar, Global Precipitation Measurement (GPM) Integrated Multi-Satellite Retrievals for GPM (IMERG), and Local Data Assimilation and Prediction System (LDAPS) data. The framework employs a Random Forest model augmented with a monthly Empirical Cumulative Distribution Function (ECDF) correction. Auxiliary predictors are incorporated to enhance physical interpretability and stability, including terrain attributes to represent orographic effects, land-cover …

From Latent Manifolds To Targeted Molecular Probes: An Interpretable, Kinome-Scale Generative Machine Learning Framework For Family-Based Kinase Ligand Design, Gennady M. Verkhivker, Ryan Kassab, Keerthi Krishnan

Mathematics, Physics, and Computer Science Faculty Articles and Research

Scaffold-aware artificial intelligence (AI) models enable systematic exploration of chemical space conditioned on protein-interacting ligands, yet the representational principles governing their behavior remain poorly understood. The computational representation of structurally complex kinase small molecules remains a formidable challenge due to the high conservation of ATP active site architecture across the kinome and the topological complexity of structural scaffolds in current generative AI frameworks. In this study, we present a diagnostic, modular and chemistry-first generative framework for design of targeted SRC kinase ligands by integrating ChemVAE-based latent space modeling, a chemically interpretable structural similarity metric (Kinase Likelihood Score), Bayesian optimization, and …

Agentic Intelligence Under Constraint: Energy, Context, And The Expansion Of Exchange, Nick Loghmani

iSchool - All Scholarship

Recent advances in agentic artificial intelligence have been driven primarily by scale: larger models, increased data, and expanding computational resources. However, rising energy costs, inference latency, and hardware constraints increasingly challenge this trajectory. This paper argues that intelligence—biological or artificial—does not primarily scale through raw computational expansion, but through the management of exchange under constraint. Drawing on cognitive science, systems theory, and prior work on exchange-based models of intelligence, the paper proposes a theoretical framework in which agentic intelligence scales through context management, proceduralization, and the assembly of reusable units of exchange. Unlike approaches that focus solely on model compression …

Ai-Driven Automatic Fault Detection Systems: Revolutionizing Modern Smart Grids, Aravind Sanikommu

Student Theses and Dissertations

The increasing complexity of current power systems, resulting from the integration of distributed generators and renewable energy sources, necessitates intelligent and adaptive fault detection schemes. Traditional protection using impedance and phasor analysis is usually weak when operating in nonlinear and transient operating conditions. Consequently, the tools of Data-driven fault classification and decision-making have gained strength under artificial intelligence (AI) and machine learning (ML) to improve grid reliability. This thesis is a proposal of an automatic fault detection and classification system based on AI applied to a smart mini-grid setting built in MATLAB/Simulink. A complete set of voltage and current data …

3d Object Tracking Registration Based On Improved Rbot Method, Jiarui Zhou, Haihua Cui, Pengcheng Li, Shihao Gu, Huipu Hao, Xifu Zhao, Anan Zhao, Tao Jiang

Journal of System Simulation

Abstract: To address the limitations of region-based object tracking (RBOT) in handling isotropic objects and scenarios with similar foreground-background colors, an improved method integrating edge features is proposed. The approach employs edge detection to extract object contours and designs a region segmentation strategy incorporated into an energy function framework to optimize internal line and edge consistency, thereby enhancing adaptability in dynamic environments and improving pose estimation accuracy. Validation through augmented reality assembly experiments on an aero-engine demonstrates that the proposed method effectively reduces rotational and translational errors, achieving initialization deviations of less than 1.5° and 0.5%, respectively. For static …

3d Reconstruction For Stadium Cad Drawings Based On Graphic Element Arrangement Pattern Analysis, Shang Ma, Mengyu Zhang, Lan Zhang, Gang Yang

Journal of System Simulation

Abstract: To address the issue of the time-consuming and labor-intensive manual conversion of two-dimensional CAD design drawings of buildings into three-dimensional models, and leveraging the characteristic that stadiums contain a large number of repetitively and regularly arranged objects, this study proposes a similar graphical element detection algorithm. This algorithm detects similarities between graphical elements by constructing their bounding boxes and calculating the L2-Norm distance, identifying all graphical elements of the same type within the CAD drawing. Furthermore, a transformation sequence detection algorithm is proposed. Based on the geometric transformation relationships between graphical elements, a geometric transformation space is defined. By …

Visual Relocalization Method Combining Region Classification And Local Feature Enhancement, Yining Wang, Yanli Liu, Guanyu Xing

Journal of System Simulation

Abstract: Visual relocalization tasks have important application value in fields such as digital twin and augmented reality. The current mainstream methods still face challenges such as mismatch between coordinate regression scale and receptive field and insufficient attention to local information. A visual relocalization method that combines region classification and local feature enhancement is proposed. The coordinate regression problem in large space is transformed into a multi-region classification problem and a coordinate regression problem inside a small scene, which significantly reduces the uncertainty of coordinate regression and makes the network globally have a large receptive field. A conditioning layer using deep …

Diffusion Model For Human Motion Generation With Fine-Grained Text And Spatial Control Signals, Binze Jiang, Wenfeng Song, Xia Hou, Shuai Li

Journal of System Simulation

Abstract: To improve the accuracy, controllability, and realism of text-driven human motion generation, a novel method is proposed that integrates fine-grained textual semantics with spatial control signals. Within the diffusion model framework, both global text tokens and body-part-level local tokens are introduced. These are encoded using CLIP to obtain corresponding features, which are then fed into the motion diffusion model to enable fine control over different body parts. Spatial guidance is used to dynamically adjust joint positions during the diffusion denoising process, ensuring that the generated motion adheres to spatial constraints. Realism guidance is incorporated to enhance the naturalness and …

Virtual Reality Rehabilitation Training System Based On Multimodal Brain-Computer Interface, Jing Qu, Kaining Fang, Shantong Zhu, Lingguo Bu

Journal of System Simulation

Abstract: The aging population has led to an increasing demand for rehabilitation for cognitive and motor functions. In response to the lack of interest in traditional rehabilitation and the absence of objective physiological assessment in existing virtual reality (VR) rehabilitation systems, a VR rehabilitation training system based on multimodal brain computer interface is developed by integrating VR interaction, near-infrared brain functional imaging, and motion capture technology. An immersive cognitive-motor integrated training environment was constructed to guide users in completing upper limb tasks. By recruiting subjects and synchronously collecting brain network data and Kinect upper limb motion parameters, multimodal assessment …

Defect Detection Method Based On Hierarchical Microscopic Feature Modeling And Simulation, Jing Zou, Xu Tan, Junji Mao, Haidong Gao, Jianrong Tan

Journal of System Simulation

Abstract: To address the challenge of detecting small and low-contrast defects in complex microscopic images, a defect method technology based on hierarchical microscopic feature modeling and simulation is proposed. The method is built on the RT-DETR (real-time detection transformer)framework to construct the HM-RTDETR (hierarchical microscopic RT-DETR) model. It maintains the global feature modeling ability of the Transformer and introduces a Dense O2O-Mosaic, a high-density one-to-one Mosaic augmentation strategy, to increase supervision density for small samples. A depthwise separable convolution (DWConv) module is used to enhance local detail extraction in microscopic textures, and a learnable PatchExpand module is applied …

Material Reconstruction From Single Image Combining Neural Networks With Singular Value Decomposition, Zhiqiang Li, Xukun Shen, Yong Hu, Xueyang Zhou, Yifan Chen

Journal of System Simulation

Abstract: The tabulated BRDFs (bidirectional reflectance distribution function) can realistically reproduce the surface appearance of objects. However, due to their high-dimensional characteristics and the fact that a single planar image contains limited reflectance information and small differences, methods for estimating tabulated BRDFs typically require complex equipment or the capture of multiple images. To address this issue, a method is proposed for reconstructing material properties from a single image by combining neural networks with singular value decomposition. The singular value decomposition is introduced to compress the material into a lower-dimensional space. The task of solving the tabulated BRDFs is simplified to …

Full-Body Co-Speech Gesture Generation Based On Spatial-Temporal Enhanced Generation Model, Shuozhe Zhang, Wenfeng Song, Xia Hou, Shuai Li

Journal of System Simulation

Abstract: Full-body co-speech gesture generation significantly enhances the interactivity of virtual digital humans, requiring generated gestures to not only align accurately with speech but also demonstrate realistic full-body dynamics. To address limitations of existing methods—Transformer-based approaches often overlook temporal features of action sequences, while diffusion model-based ones inadequately capture spatial correlations between body parts, a full-body action generation method integrating diffusion models, Mamba, and attention mechanisms is proposed. We introduce the spatial self-attention-temporal state space model (STMamba Layer) as the core of denoising network to extract
inter-part spatial features and intra-part temporal features, thus enhancing action quality and diversity. …

Vrbt: Vr Badminton Training With Multitask Injury Alerts Based On Lightweight 3d Skeletal Reconstruction, Yuning Zhu, Meng Yang, Tianyue Chen, Weiliang Meng

Journal of System Simulation

Abstract: To overcome the limitations of traditional badminton training, a VR training method that integrates multiple models for collaborative simulation is proposed. A "perception-decision- interaction" framework is developed within Unity, featuring diverse training modules powered by a physics engine for realistic trajectory simulation. The system employs a lightweight MHFormer for 3D pose estimation and a novel multi-task model (enhanced injury prediction system, EIPS) that combines random forest and XGBoost to jointly assess injury risk. This approach offers a solution for balancing real-time performance with accuracy in skeleton reconstruction and enables personalized training through dynamic risk assessment.

Addressing The Void Of Ai Policies In Education For Students With Specific Learning Disabilities, Mikyung Shin, Fatmana Deniz, Latesha Watson, Cynthia Dieterich, Kathy B. Ewoldt, Friggita Johnson, Jennifer E. Kong, Sung Hee Lee, April Whitehurst

Education Faculty Articles and Research

The purpose of this study was to identify the current state of artificial intelligence (AI) policies in U.S. education and propose actionable recommendations through large language model–based topic modeling and Delphi surveys. Out of 12 policy documents released between 2015 and 2025, only two documents (National Center for Learning Disabilities, 2024; W.A. v. Clarksville/Montgomery County School System, 2024) specifically addressed learning disabilities. Policy documents addressing topics such as AI-driven risk assessment, data protection, legal risk management, and ethical guidelines covering other disabilities and general AI in education policy were provided as baselines that could be discussed and validated through …

Military Metaverse: Conceptual Connotation, Construction And Application Framework, Key Issues, Dayong Liu, Zhiming Dong, Jiancheng Gao

Journal of System Simulation

Abstract: Based on the analysis of the concept of the metaverse, the military metaverse concept model is established and compared with virtual-real fusion systems such as the digital twin battlefield, analyzing its core characteristics and construction significance. To accelerate the construction of the military metaverse, an overall logical architecture for the construction and application of the military metaverse is designed, the concept of military metaverse primitives is proposed, and the technical architecture is designed. The main application directions of the military metaverse are analyzed, and the construction stage division and overall thinking are provided. The key issues in construction and …

Virtual-Real Fusion Simulation Technology And Application Research For Industrial Control Systems Cybersecurity Of Process Manufacturing, Xinwei Wang, Jinjiang Wang, Zheng Wang, Laibin Zhang

Journal of System Simulation

Abstract: Aiming at the problem that the industrial control system in the process manufacturing industry lacks an effective attack and defense drill platform when facing network attacks, it is difficult to truly simulate the attack situation, verify the protective measures, and accurately evaluate the impact of attacks on the physical system, an industrial control cybersecurity simulation technology based on virtual-real fusion is proposed to build an efficient attack and defense drill range. The industrial control cybersecurity simulation architecture based on virtual-real fusion is designed, and the consistency analysis of virtual-real fusion data is carried out. At the same time, …

Spatio-Temporal Swin Transformer-Based Flow-Solid Coupling Interaction Sequence Image Prediction Network, Changjun Zou, Zhiyu Ge, Chenxi Zhong

Journal of System Simulation

Abstract: To address limitations in modeling long-term dependencies and multi-scale features in fluidstructure interaction scenarios, a spatiotemporal deep learning model (SwinLSTM) integrating ConvLSTM and Swin Transformer is proposed. The model employs a gated spatiotemporal attention mechanism that dynamically embeds Swin Transformer's window-based multi-head self-attention into ConvLSTM's output gate, enabling adaptive temporal-spatial feature coupling, and designs a multi-level ConvLSTM framework to hierarchically capture complex spatiotemporal correlations. Experiments on a self-built fluid-interaction dataset show that our method achieves the highest PSNR and leading SSIM scores, with superior performance in preserving vortex details and boundary consistency. This work provides an efficient solution …

Pl-Mamba: A 3d Point Cloud Semantic Segmentation Network Based On Bimodal Fusion, He Zhu, Feng Zhou, Mengxiao Zhu, Ju Dai

Journal of System Simulation

Abstract: To enhance the semantic discrimination capability in point cloud semantic segmentation, a 3D point cloud semantic segmentation network named PL-Mamba is proposed, which is centered on the fusion of point cloud (P) and language (L) dual modalities. This method takes PointMamba as the backbone network, leveraging its excellent long-sequence modeling and global perception capabilities. It introduces a language prompt mechanism and uses a pretrained language model BERT to encode the context of category labels, obtaining semantically rich text features. The text information serves as a language guided token and is deeply integrated with point cloud features through cross modal …

Dehpr: A Diffusion-Based End-To-End Hand Pose Reconstruction Network, Guoqiong Liao, Longjie Huang, Qingxin Li, Jiajun Zhang, Kefan Chen

Journal of System Simulation

Abstract: Traditional methods such as convolutional neural networks (CNNs) and Transformers suffer from strong dependence on large-scale annotated data and limited generalization capability when dealing with hand pose reconstruction in complex scenarios. To address these issues, a diffusion-based end-to-end hand pose reconstruction network (DEHPR) is proposed. This method employs a diffusion model to directly generate and refine 3D predictions, thereby reducing spatial uncertainties inherent in 2D-to-3D modeling paradigms. By incorporating an end-to-end framework that reprojects multiple 3D candidate predictions to select optimal joint positions, the approach ultimately produces accurate hand pose estimations. Comprehensive evaluations conducted on HO3D V2, DexYCB, …

Cross-Domain Crowd Counting Model Based On Frequency Domain Enhancement, De Zhang, Zishan Liang, Ningning Liu

Journal of System Simulation

Abstract: Crowd counting takes video surveillance data as input and can be applied to the construction of city digital twin platforms, virtual city modeling and smart city management, etc. However, when there are data domain differences between the application scenario and training scenario, counting performance often significantly decreases. A cross-domain crowd counting model based on frequency domain enhancement is proposed. To alleviate the distribution differences between domains, a frequency domain feature enhancement module and a domain invariant frequency domain adapter module are constructed: the former uses discrete cosine transform to extract key statistical features to enhance spatial representation ability, while …

Research On Real-Time Animatable Human Avatar Generation Via 3d Gaussian Splatting, Yuyou Zhong, Xukun Shen, Yong Hu

Journal of System Simulation

Abstract: Real-time animatable 3D human avatar generation technology hold significant application value in fields such as virtual reality and remote collaboration. To address the limitations of existing methods in detail modeling, real-time performance, and robustness under novel pose driving, an efficient human avatar generation and driving method based on 3D Gaussian splatting (3DGS) is proposed. This method integrates optimized parametric human reconstruction, tri-plane feature encoding, and dynamic offset prediction to achieve efficient modeling from monocular video input. By introducing a skeleton binding and visibility analysis strategy, while designing a multi-scale regularization loss to address the overfitting problem. Simulation experiments demonstrate …

Inverse Kinematics 3d Human Modeling Simulation Based On Multi-View Vision, Guoyu Fang, Yanze Li, Kai Chen, Xiaodong Zhao, Zizhuo Hu, Mingshi Yang, Wanqing Wu, Zichen Wang, Wenkai Guo

Journal of System Simulation

Abstract: In autonomous driving simulation and industrial virtual reality simulation, there is a high demand for accuracy and robustness in 3D human body modeling. However, current joint-based human modeling approaches suffer from issues such as continuous modeling jitter, local distortion, and poor adaptability to occlusion, which degrade model quality and limit the development of practical applications such as intelligent driving and digital factories. To address these challenges, this paper proposes a multi-view vision-based inverse kinematics 3D human modeling method using a vector quantized variational autoencoder(IK-VQ-VAE). By integrating joint training with an automatic variational gradient descent approach, the proposed method achieves …

Law Schools Should Teach How To Integrate Ai Tools Into Practice, Robert A. Mackenzie, David J. Reiss

Cornell Law Faculty Publications

Now that artificial intelligence tools for lawyers are widely available, we decided to integrate them for a semester in our Entrepreneurship Clinic. We have some important takeaways for legal education in general and the transactional practice of law in particular.

First, employers and educators need to account for law students who already are using AI tools in their legal work and guide new lawyers about how to use such tools appropriately.

Second, different AI products lead to wildly different results. Just demonstrating this to law students is very valuable, as it dispels the notion that AI responses can replace their …

A Robust Deep Learning Ensemble Framework For Waterbody Detection Using High-Resolution X-Band Sar Under Data-Constrained Conditions, Soyeon Choi, Seung Hee Kim, Son V. Nghiem, Menas Kafatos, Minha Choi, Jinsoo Kim, Yangwon Lee

Institute for ECHO Articles and Research

Accurate delineation of inland waterbodies is critical for applications such as hydrological monitoring, disaster response preparedness and response, and environmental management. While optical satellite imagery is hindered by cloud cover or low-light conditions, Synthetic Aperture Radar (SAR) provides consistent surface observations regardless of weather or illumination. This study introduces a deep learning-based ensemble framework for precise inland waterbody detection using high-resolution X-band Capella SAR imagery. To improve the discrimination of water from spectrally similar non-water surfaces (e.g., roads and urban structures), an 8-channel input configuration was developed by incorporating auxiliary geospatial features such as height above nearest drainage (HAND), slope, …

Stylespade: Realistic Image Augmentation For Robust Infrastructure Crack Segmentation Via Ensemble Learning, Jaeung Sim, Menas Kafatos, Seung Hee Kim, Yangwon Lee

Institute for ECHO Articles and Research

The rapid deterioration of global infrastructure necessitates precise and automated crack detection technologies for proactive maintenance. However, deep learning-based segmentation models often suffer from a scarcity of diverse, high-quality labeled datasets. This study proposes StyleSPADE, a novel conditional image generation model that integrates semantic masks and style images to synthesize realistic crack data with diverse background textures while preserving precise geometric morphology. To validate the effectiveness of the generated data, we conducted extensive semantic segmentation tasks using Transformer-based (Mask2Former, Swin-UPerNet) and CNN-based (K-Net) models. Experimental results demonstrate that StyleSPADE-based augmentation significantly outperforms baseline models, achieving a Crack IoU of 0.6376 …

Are You An Ai Convert Yet?, Essraa Nawar

Library Articles and Research

"At one point that evening, after the conversation had moved from travel to work and then to responsibility, Marium paused and asked me what I did. It was not the transactional question that so often fills conference hallways, asked politely and quickly abandoned, but a genuine inquiry. When I told her that I chair the Artificial Intelligence Committee at Leatherby Libraries at Chapman University, and that my work centers on AI literacy, governance, and institutional decision-making rather than promotion or blind adoption, something subtle changed."