arXiv subjects

Sean Kalaycioglu

Publications and source records attributed to Sean Kalaycioglu.

5 recordsLinked to original sources

arXiv2026

Forecasting Land Art Under Climate Scenarios

Robert Smithson's 1970 land artwork Spiral Jetty, located in the north arm of Utah's Great Salt Lake, provides a fixed remote-sensing target whose visual complexity reflects hydroclimatic conditions. A companion study analyzed 1,744 co-registered Landsat 4-9 and Sentinel-2 image chips spanning every year and month from 1984 to 2025. It found robust relationships between coarse-scale permutation entropy, mean intensity, and the third principal component of ResNet50 avg-pool embeddings, and lake elevation, regional temperature, and cumulative CO2. It also showed that image complexity leads lake stage by about three years and that the long-term trend is non-monotonic, with decline after 2015. Building on those findings, this paper develops a two-stage forecasting pipeline. Stage 1 applies IPCC AR6 SSP1-2.6, SSP2-4.5, and SSP5-8.5 temperature changes to forecast regional temperature, north- and south-arm lake elevation, salinity, and cumulative CO2 for 2030 and 2050. Stage 2a projects 14 image-complexity features using linear and Random Forest regressions trained on the 42-year record. All six scenario-year combinations move the inputs outside the 1984-2025 training distribution. The Random Forest model therefore saturates near the post-2015 dry-playa regime, while a threshold-based hydrological interpretation classifies Spiral Jetty as fully exposed in every scenario. Stage 2b specifies a climate-conditioned latent-diffusion framework using Stable Diffusion XL fine-tuned with LoRA on the 1,744 chips, ControlNet conditioning on the climate vector, and a hydrological physics mask for ensemble image synthesis. Code is provided, and validation results will be released after diffusion training. We conclude by discussing ethical implications of generative speculation on cultural heritage and outlining a roadmap for forecasting at Sun Tunnels, Double Negative, Lightning Field, and Roden Crater.

cs.IT↗

arXiv2026

Interpretable Image-Level Acne Severity Grading via EfficientNet-B0 Transfer Learning and Grad-CAM

Acne vulgaris affects most adolescents and many adults. Accurate severity grading guides treatment, monitoring, and clinical trial endpoints, but manual assessment using the Investigator's Global Assessment or Hayashi criteria is limited by inter-rater variability and inconsistent imaging conditions. We developed a four-class acne severity classifier based on the Hayashi criteria using transfer learning with an ImageNet-pretrained EfficientNet-B0 model. The model was fine-tuned on the public ACNE04 dataset of 2,983 labeled images using AdamW optimization, geometric and photometric augmentation, and checkpoint selection based on validation macro-F1. On a held-out stratified 15 percent test set, the classifier achieved 93.5 percent accuracy and 94.4 percent macro-F1, with per-class F1 scores from 0.92 to 0.97. Eighty-three percent of errors occurred between adjacent grades. Quadratic-weighted Cohen's kappa was 0.956, with a 95 percent confidence interval of 0.935 to 0.973. Bootstrap confidence intervals indicated stable performance. Grad-CAM visualizations from the final convolutional block focused on clinically relevant facial regions, including the forehead, cheeks, and chin. The complete pipeline is provided as functionally equivalent open-source implementations in Python using PyTorch and timm, and in MATLAB R2026a. The software includes a clinician-facing inference interface and a fallback backbone option that supports operation without specialized pretrained-weight packages. These results show that lightweight transfer learning can provide accurate, balanced, and interpretable acne severity grading while offering a reproducible cross-platform reference for future prospective and device-stratified clinical validation.

cs.CV↗

arXiv2025

AI-Powered Legal Intelligence System Architecture: A Comprehensive Framework for Automated Legal Consultation and Analysis

This paper introduces the Legal Intelligence and Client Engagement System (LICES), a novel architecture designed to redefine legal consultation services through the systematic integration of advanced artificial intelligence, natural language processing, and federated legal databases. The proposed system uniquely harmonizes the sophisticated reasoning capabilities of large language models with authoritative legal information repositories, including CanLII, LexisNexis, WestLaw, the Justice Laws Website, and Supreme Court records. The architecture employs a multi-layered design that encompasses a dynamic client interface, a robust legal processing server, and an AI-driven knowledge integration layer. Crucially, the system embeds stringent, multi-stage conflict-of-interest protocols and automated compliance checks to ensure adherence to professional ethics. Through detailed system modeling and architectural design, we demonstrate how the integration of speech recognition, document analysis, and a dynamic interview process has the potential to significantly enhance the efficacy and accessibility of legal services. Performance evaluations indicate that the LICES architecture can reduce preliminary legal research and case assessment time by more than 90% compared to traditional paralegal benchmarks while achieving more than 98% of accuracy in citation and legal issue identification This research contributes a scalable, secure, and ethically grounded framework for automated legal services, offering a validated blueprint for navigating multi-jurisdictional complexities and the fragmented landscape of legal data.

cs.CY↗

arXiv2024

NMPC and Deep Learning-Based Vibration Control of Satellite Beam Antenna Dynamics Using PZT Actuators and Sensors

This paper presents a novel approach for vibration control of satellite-based flexible beam-type antennas using Nonlinear Model Predictive Control (NMPC) and Deep Learning techniques. The developed control system leverages piezoelectric (PZT) actuators and sensors to manage the coupled attitude and structural dynamics of the satellite, improving precision and stability. We propose a detailed coupled dynamics model that integrates both satellite attitude and beam structural dynamics, considering the effects of PZT-based actuators. Through MATLAB/Simulink simulations, we demonstrate the effectiveness of the combined NMPC and Deep Learning framework in reducing structural vibrations, achieving faster response times, and enhancing overall control accuracy. The results indicate that the proposed system provides a robust solution for controlling flexible beam-type satellite antennas in space environments.

eess.SY↗

arXiv2024

Intelligent Magnetic Inspection Robot for Enhanced Structural Health Monitoring of Ferromagnetic Infrastructure

This paper presents an innovative solution to the issue of infrastructure deterioration in the U.S., where a significant portion of facilities are in poor condition, and over 130,000 steel bridges have exceeded their lifespan. Aging steel structures face corrosion and hidden defects, posing major safety risks. The Silver Bridge collapse, resulting from an undetected flaw, highlights the limitations of manual inspection methods, which often miss subtle or concealed defects. Addressing the need for improved inspection technology, this work introduces an AI-powered magnetic inspection robot. Equipped with magnetic wheels, the robot adheres to and navigates complex ferromagnetic surfaces, including challenging areas like vertical inclines and internal corners, enabling thorough, large-scale inspections. Utilizing MobileNetV2, a deep learning model trained on steel surface defects, the system achieved an 85% precision rate across six defect types. This AI-driven inspection process enhances accuracy and reliability, outperforming traditional methods in defect detection and efficiency. The findings suggest that combining robotic mobility with AI-based image analysis offers a scalable, automated approach to infrastructure inspection, reducing human labor while improving detection precision and the safety of critical assets.

cs.RO↗