Baseline (sea)
View article: Projecting harmful algal blooms in North Biscayne Bay using machine learning and bias-corrected climate scenarios
Projecting harmful algal blooms in North Biscayne Bay using machine learning and bias-corrected climate scenarios Open
Study area North Biscayne Bay, downstream of urbanized Miami-Dade County, is an ecological hot spot and frequently impacted by harmful algal blooms (HABs). Study focus This study combines machine learning models with bias-corrected climate…
View article: Morphology-driven Map Processing and Key-point Optimization for Enhanced Path Planning in ROS-based Autonomous Vehicles
Morphology-driven Map Processing and Key-point Optimization for Enhanced Path Planning in ROS-based Autonomous Vehicles Open
Path planning is a critical component of autonomous vehicles, intelligent transportation, and robotic navigation. However, conventional algorithms such as A*, Dijkstra, bidirectional A*, and RRT often suffer from local optima, redundant tu…
View article: Multi-hazards in Scandinavia: impacts and risks from compound heatwaves, droughts and wildfires
Multi-hazards in Scandinavia: impacts and risks from compound heatwaves, droughts and wildfires Open
In the summer of 2018, large parts of Scandinavia faced record-breaking heat and drought, leading to increased mortality, agricultural water shortages, hydropower deficits, and higher energy prices. The 2018 heatwave coupled with droughts …
View article: Low Financial Risk of Default and Productive Use of Assets Through Hidden Markov Models
Low Financial Risk of Default and Productive Use of Assets Through Hidden Markov Models Open
This paper analyzes solvency dynamics in Ecuador’s mutualist segment by modeling the joint behavior of the productive-assets-to-total-assets ratio (PATR) and portfolio-specific delinquency rates. Using monthly supervisory data from the Sup…
View article: A Comprehensive Evaluation of a Retrieval-Augmented Generation (RAG) Pipeline for Document Question Answering Using FAISS and Llama3
A Comprehensive Evaluation of a Retrieval-Augmented Generation (RAG) Pipeline for Document Question Answering Using FAISS and Llama3 Open
Retrieval-Augmented Generation (RAG) has emerged as an effective framework for enhancing factual accuracy in Large Language Models (LLMs) by grounding generated responses in retrieved document context. This paper presents the design, imple…
View article: Semantic-aware Multi-Scale Simplification of Urban-Scale 3D Real-Scene Mesh Models
Semantic-aware Multi-Scale Simplification of Urban-Scale 3D Real-Scene Mesh Models Open
Recent advances in measurement technologies have significantly improved the accuracy of multi-scale 3D reconstruction, yet the resulting large-scale data with inherent redundancy pose challenges for storage and real-time rendering. This pa…
View article: Trajectories of affective disorders—the central structures of CRC/TRR 393
Trajectories of affective disorders—the central structures of CRC/TRR 393 Open
The recurrent and often unpredictable course of affective disorders poses a critical challenge for long-term patient care. The CRC/TRR 393 consortium has established an ambitious longitudinal study, the German Mental Health Cohort (GEMCO),…
View article: The Remote Fingerprint of AMOC: Spatiotemporal Shifts in Upwelling Systems and Coastal Resilience
The Remote Fingerprint of AMOC: Spatiotemporal Shifts in Upwelling Systems and Coastal Resilience Open
The Atlantic Meridional Overturning Circulation (AMOC) is a crucial component of the global climate system, responsible for significant heat transport within the Atlantic Ocean. While its direct impacts on North Atlantic climate are well-d…
View article: MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning
MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning Open
Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where dangerous instructions pose significant risks. Existing methods often suffer from either high …
View article: KnotSegNet3D: High Precision Knot Segmentation in Norway Spruce CT Logs via Mixed Training and Fine-Tuned Transfer Learning
KnotSegNet3D: High Precision Knot Segmentation in Norway Spruce CT Logs via Mixed Training and Fine-Tuned Transfer Learning Open
CT scans offer a valuable way to automatically segment knots, however wet logs pose a crucial challenge for sawmills, due to the similar intensity between water saturated sapwood and the knot. Most existing approaches rely on traditional s…
View article: PDCA-Based Methodology for the Evaluation of Energy Efficiency in the Industrial Sector
PDCA-Based Methodology for the Evaluation of Energy Efficiency in the Industrial Sector Open
Reducing energy consumption and improving energy efficiency are essential objectives in the productive sector to ensure economic growth and reduce emissions. However, some energy management models do not include tools such as the balanced …
View article: Calibrated Variant Effect Prediction at the Residue Level Using Conditional Score Distributions
Calibrated Variant Effect Prediction at the Residue Level Using Conditional Score Distributions Open
Effective clinical use of variant effect prediction (VEP) requires models that are both accurate and well-calibrated. Calibration refers to a model's ability to produce meaningful and reliable probability estimates. Here, we propose a prac…
View article: GC-GAT: An integrated approach combining grid calculation and graph attention network for geographic knowledge graph reasoning
GC-GAT: An integrated approach combining grid calculation and graph attention network for geographic knowledge graph reasoning Open
Geographic knowledge graph (KG) reasoning enables the inference of missing entities and relations, a fundamental step toward constructing comprehensive geospatial knowledge systems. However, prevailing approaches often struggle with the ac…
View article: Robust Activity Recognition via Redundancy-Aware CNNs and Novel Pooling for Noisy Mobile Sensor Data
Robust Activity Recognition via Redundancy-Aware CNNs and Novel Pooling for Noisy Mobile Sensor Data Open
This paper proposes a robust convolutional neural network (CNN) architecture for human activity recognition (HAR) using smartphone accelerometer data, evaluated on the WISDM dataset. We introduce two novel pooling mechanisms—Pooling A (Ext…
View article: Figure S7 from Validation of a Genetic-Enhanced Risk Prediction Model for Colorectal Cancer in a Large Community-Based Cohort
Figure S7 from Validation of a Genetic-Enhanced Risk Prediction Model for Colorectal Cancer in a Large Community-Based Cohort Open
Supplementary Figure S7 shows the Sex-specific estimated baseline incidence rate of CRC based on SEER18 (2007-2015) CRC rate in European population.
View article: Supplementary Table 1 from Low-Carbohydrate Diet Score and the Risk of Colorectal Cancer: Findings from the Singapore Chinese Health Study
Supplementary Table 1 from Low-Carbohydrate Diet Score and the Risk of Colorectal Cancer: Findings from the Singapore Chinese Health Study Open
Supplementary Table S1 describes baseline characteristics of participants
View article: Marine cold spells in the Baltic Sea
Marine cold spells in the Baltic Sea Open
Marine cold spells, characterized by anomalously low sea surface temperatures, play a crucial role in shaping marine ecosystems and have significant socioeconomic implications. Unlike the extensively studied marine heatwaves, research on m…
View article: Supplemental Table 4 from Prospective and Cross-sectional Associations of the Rectal Tissue Microbiome with Colorectal Adenoma Recurrence
Supplemental Table 4 from Prospective and Cross-sectional Associations of the Rectal Tissue Microbiome with Colorectal Adenoma Recurrence Open
Supplemental Table 4 shows the cross-sectional multivariablea associations of baseline and year-1 alpha diversity with adenoma/polyp characteristics in the four-year Polyp Prevention Trial, 1991-1998
View article: Co-Training Vision Language Models for Remote Sensing Multi-task Learning
Co-Training Vision Language Models for Remote Sensing Multi-task Learning Open
With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple tasks through multi-task learning (MTL). Compared to single-…
View article: Contextual Multi-Armed Bandits for Dynamic News Recommendation: An Empirical Evaluation
Contextual Multi-Armed Bandits for Dynamic News Recommendation: An Empirical Evaluation Open
With the advent of the information explosion era, personalized news recommendation faces critical challenges including cold start problems, real-time changes in user preferences, and information filter bubbles. Traditional collaborative fi…
View article: Baseline temperature variability shapes the geographical distribution of future hot extremes under anthropogenic warming
Baseline temperature variability shapes the geographical distribution of future hot extremes under anthropogenic warming Open
View article: Pattern–Phase Resilience to Acute Shocks in Honeybee Colonies
Pattern–Phase Resilience to Acute Shocks in Honeybee Colonies Open
We propose a theoretical framework in which honeybee colonies are treated as topological pattern–phase systems that exhibit a characteristic, measurable form of trauma resilience. Rather than describing st…
View article: The Remote Fingerprint of AMOC: Spatiotemporal Shifts in Upwelling Systems and Coastal Resilience
The Remote Fingerprint of AMOC: Spatiotemporal Shifts in Upwelling Systems and Coastal Resilience Open
The Atlantic Meridional Overturning Circulation (AMOC) is a crucial component of the global climate system, responsible for significant heat transport within the Atlantic Ocean. While its direct impacts on North Atlantic climate are well-d…
View article: Comment Thread: Philosophical Uncertainty Regarding the Ontological Status of Trent Slade
Comment Thread: Philosophical Uncertainty Regarding the Ontological Status of Trent Slade Open
This image documents a highlighted YouTube comment from the video “Trolling Trent Slade.”The commenter expresses uncertainty about whether the channel creator is a real human being or an artificially generated persona—an increasingly commo…
View article: Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models
Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models Open
Denoising Diffusion Probabilistic Models (DDPMs) can generate synthetic timeseries data to help improve the performance of a classifier, but their sampling process is computationally expensive. We address this by combining implicit diffusi…
View article: MRI-derived extracellular volume fraction as a prognostic biomarker for early recurrence after R0 resection of pancreatic ductal adenocarcinoma
MRI-derived extracellular volume fraction as a prognostic biomarker for early recurrence after R0 resection of pancreatic ductal adenocarcinoma Open
View article: Modeling of Medical Waste Generation in Dental Clinics Affiliated to the Provincial Health Directorate in Kastamonu: PLS and Gradient Boosting Approaches
Modeling of Medical Waste Generation in Dental Clinics Affiliated to the Provincial Health Directorate in Kastamonu: PLS and Gradient Boosting Approaches Open
Effective medical waste planning relies on the reliable estimation of waste volumes. As operational factors diversify, traditional linear regressions often fail to capture the underlying structure, whereas latent variable–based and ensembl…
View article: Hybrid Control for Robotic Nut Tightening Task
Hybrid Control for Robotic Nut Tightening Task Open
An autonomous robotic nut tightening system for a serial manipulator equipped with a parallel gripper is proposed. The system features a hierarchical motion-primitive-based planner and a control-switching scheme that alternates between for…
View article: ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Features
ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Features Open
This paper investigates sequence-to-sequence Transformer models for automatic speech recognition (ASR) error correction in low-resource Burmese, focusing on different feature integration strategies including IPA and alignment information. …
View article: PAMP ULTRA: Breakthrough in Space Propulsion with 99.5% Ionization Efficiency and 9.85N Thrust Using Multi-Stage Hybrid Technology
PAMP ULTRA: Breakthrough in Space Propulsion with 99.5% Ionization Efficiency and 9.85N Thrust Using Multi-Stage Hybrid Technology Open
This research presents the experimental development and performance validation of PAMP ULTRA (Phased Array Microwave Plasma - Ultimate Laboratory Research Advancement), a revolutionary electric propulsion system achieving unprecedented 99.…