PyTorchKR Papers

최신 논문

총 7,781편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2503.18849

Application of Physics-Informed Neural Networks for Solving the Inverse Advection-Diffusion Problem to Localize Pollution Sources

This paper investigates the application of Physics-Informed Neural Networks (PINNs) for solving the inverse advection-diffusion problem to localize pollution sources. The study focuses on optimizing neural network architectures to accurately model pollutant dispersion dynamics under diverse conditions, including scenarios with weak and strong winds and multiple pollution sources. Various PINN configurations are evaluated, showing the strong dependence of solution accuracy on hyperparameter selection. Recommendations for efficient PINN configurations are provided based on these comparisons. The approach is tested across multiple scenarios and validated using real-world data that accounts for atmospheric variability. The results demonstrate that the proposed methodology achieves high accuracy in source localization, showcasing the stability and potential of PINNs for addressing environmental monitoring and pollution management challenges under complex weather conditions.

arXiv:2503.18161

Active Inference for Energy Control and Planning in Smart Buildings and Communities

Active Inference (AIF) is emerging as a powerful framework for decision-making under uncertainty, yet its potential in engineering applications remains largely unexplored. In this work, we propose a novel dual-layer AIF architecture that addresses both building-level and community-level energy management. By leveraging the free energy principle, each layer adapts to evolving conditions and handles partial observability without extensive sensor information and respecting data privacy. We validate the continuous AIF model against both a perfect optimization baseline and a reinforcement learning-based approach. We also test the community AIF framework under extreme pricing scenarios. The results highlight the model's robustness in handling abrupt changes. This study is the first to show how a distributed AIF works in engineering. It also highlights new opportunities for privacy-preserving and uncertainty-aware control strategies in engineering applications.

arXiv:2503.17293

Leveraging statistical models to improve pre-season forecasting and in-season management of a recreational fishery

Effective management of recreational fisheries requires accurate forecasting of future harvests and real-time monitoring of ongoing harvests. Traditional methods that rely on historical catch data to predict short-term harvests can be unreliable, particularly if changes in management regulations alter angler behavior. In contrast, statistical modeling approaches can provide faster, more flexible, and potentially more accurate predictions, enhancing management outcomes. In this study, we developed and tested models to improve predictions of Gulf of Mexico gag harvests for both pre-season planning and in-season monitoring. Our best-fitting model outperformed traditional methods (i.e., estimates derived from historical average harvest) for both cumulative pre-season projections and in-season monitoring. Notably, our modeling framework appeared to be more accurate in more recent, shorter seasons due to its ability to account for effort compression. A key advantage of our framework is its ability to explicitly quantify the probability of exceeding harvest quotas for any given season duration. This feature enables managers to evaluate trade-offs between season duration and conservation goals. This is especially critical for vulnerable, highly targeted stocks. Our findings also underscore the value of statistical models to complement and advance traditional fisheries management approaches.

arXiv:2503.18675

Corporate Finance in the Age of Fintech: Scenarios and Challenges

Blockchain is a technological innovation that has the potential to radically change our financial markets by providing an alternative management approach to the "promise market", which is the foundation of our financial systems. Its disruptive potential also extends to corporate finance, where blockchain is beginning to influence valuation methods and capital allocation strategies, offering new perspectives on how companies are assessed and financed. However, for a new financial architecture based on blockchain and advancements in technology -- what is commonly referred to as Fintech -- to replace, in whole or in part, traditional finance, it will need to overcome significant challenges such as regulation, environmental sustainability, its association with illegal activities, and achieving greater efficiency in cryptocurrency markets. For this reason, the future of Fintech is likely to be more conventional -- yet also more transparent, efficient, and regulated -- ultimately evolving to resemble the traditional finance we know.

arXiv:2503.18592

The Role of Artificial Intelligence in Enhancing Insulin Recommendations and Therapy Outcomes

The growing worldwide incidence of diabetes requires more effective approaches for managing blood glucose levels. Insulin delivery systems have advanced significantly, with artificial intelligence (AI) playing a key role in improving their precision and adaptability. AI algorithms, particularly those based on reinforcement learning, allow for personalised insulin dosing by continuously adapting to an individual's responses. Despite these advancements, challenges such as data privacy, algorithm transparency, and accessibility still need to be addressed. Continued progress and validation in AI-driven insulin delivery systems promise to improve therapy outcomes further, offering people more effective and individualised management of their diabetes. This paper presents an overview of current strategies, key challenges, and future directions.

arXiv:2503.18265

Risk Management for Distributed Arbitrage Systems: Integrating Artificial Intelligence

Effective risk management solutions become absolutely crucial when financial markets embrace distributed technology and decentralized financing (DeFi). This study offers a thorough survey and comparative analysis of the integration of artificial intelligence (AI) in risk management for distributed arbitrage systems. We examine several modern caching techniques namely in memory caching, distributed caching, and proxy caching and their functions in enhancing performance in decentralized settings. Through literature review we examine the utilization of AI techniques for alleviating risks related to market volatility, liquidity challenges, operational failures, regulatory compliance, and security threats. This comparison research evaluates various case studies from prominent DeFi technologies, emphasizing critical performance metrics like latency reduction, load balancing, and system resilience. Additionally, we examine the problems and trade offs associated with these technologies, emphasizing their effects on consistency, scalability, and fault tolerance. By meticulously analyzing real world applications, specifically centering on the Aave platform as our principal case study, we illustrate how the purposeful amalgamation of AI with contemporary caching methodologies has revolutionized risk management in distributed arbitrage systems.

arXiv:2503.18255

The Human-Machine Identity Blur: A Unified Framework for Cybersecurity Risk Management in 2025

The modern enterprise is facing an unprecedented surge in digital identities, with machine identities now significantly outnumbering human identities. This paper examines the cybersecurity risks emerging from what we define as the "human-machine identity blur" - the point at which human and machine identities intersect, delegate authority, and create new attack surfaces. Drawing from industry data, expert insights, and real-world incident analysis, we identify key governance gaps in current identity management models that treat human and machine entities as separate domains. To address these challenges, we propose a Unified Identity Governance Framework based on four core principles: treating identity as a continuum rather than a binary distinction, applying consistent risk evaluation across all identity types, implementing continuous verification guided by zero trust principles, and maintaining governance throughout the entire identity lifecycle. Our research shows that organizations adopting this unified approach experience a 47 percent reduction in identity-related security incidents and a 62 percent improvement in incident response time. We conclude by offering a practical implementation roadmap and outlining future research directions as AI-driven systems become increasingly autonomous.

arXiv:2503.17730

Aportes para el cumplimiento del Reglamento (UE) 2024/1689 en robótica y sistemas autónomos

Cybersecurity in robotics stands out as a key aspect within Regulation (EU) 2024/1689, also known as the Artificial Intelligence Act, which establishes specific guidelines for intelligent and automated systems. A fundamental distinction in this regulatory framework is the difference between robots with Artificial Intelligence (AI) and those that operate through automation systems without AI, since the former are subject to stricter security requirements due to their learning and autonomy capabilities. This work analyzes cybersecurity tools applicable to advanced robotic systems, with special emphasis on the protection of knowledge bases in cognitive architectures. Furthermore, a list of basic tools is proposed to guarantee the security, integrity, and resilience of these systems, and a practical case is presented, focused on the analysis of robot knowledge management, where ten evaluation criteria are defined to ensure compliance with the regulation and reduce risks in human-robot interaction (HRI) environments.

arXiv:2503.17515

A Predictive Services Architecture for Efficient Airspace Operations

Predicting air traffic congestion and flow management is essential for airlines and Air Navigation Service Providers (ANSP) to enhance operational efficiency. Accurate estimates of future airport capacity and airspace density are vital for better airspace management, reducing air traffic controller workload and fuel consumption, ultimately promoting sustainable aviation. While existing literature has addressed these challenges, data management and query processing remain complex due to the vast volume of high-rate air traffic data. Many analytics use cases require a common pre-processing infrastructure, as ad-hoc approaches are insufficient. Additionally, linear prediction models often fall short, necessitating more advanced techniques. This paper presents a data processing and predictive services architecture that ingests large, uncorrelated, and noisy streaming data to forecast future airspace system states. The system continuously collects raw data, periodically compresses it, and stores it in NoSQL databases for efficient query processing. For prediction, the system learns from historical traffic by extracting key features such as airport arrival and departure events, sector boundary crossings, weather parameters, and other air traffic data. These features are input into various regression models, including linear, non-linear, and ensemble models, with the best-performing model selected for predictions. We evaluate this infrastructure across three prediction use cases in the US National Airspace System (NAS) and a segment of European airspace, using extensive real operations data, confirming that our system can predict future system states efficiently and accurately.

arXiv:2503.17500공식 코드 · Papers with Code

Variance Control via Weight Rescaling in LLM Pre-training

The outcome of Large Language Model (LLM) pre-training strongly depends on weight initialization and variance control strategies. Although the importance of initial variance control has been well documented in neural networks in general, the literature on initialization and management of its growth during LLM pre-training, specifically, is somewhat sparse. In this paper, we introduce the Layer Index Rescaling (LIR) weight initialization scheme, and the Target Variance Rescaling (TVR) variance control strategy. Experiments on a 1B parameter LLaMA model demonstrate that better variance management using these techniques yields substantial improvements in downstream task performance (up to 4.6% on common pre-training benchmarks) and reduces extreme activation values, thus mitigating challenges associated with quantization and low-precision training. Our code is available at: https://github.com/bluorion-com/weight_rescaling.

arXiv:2503.14552

Fire and Smoke Datasets in 20 Years: An In-depth Review

Fire and smoke phenomena pose a significant threat to the natural environment, ecosystems, and global economy, as well as human lives and wildlife. In this particular circumstance, there is a demand for more sophisticated and advanced technologies to implement an effective strategy for early detection, real-time monitoring, and minimizing the overall impacts of fires on ecological balance and public safety. Recently, the rapid advancement of Artificial Intelligence (AI) and Computer Vision (CV) frameworks has substantially revolutionized the momentum for developing efficient fire management systems. However, these systems extensively rely on the availability of adequate and high-quality fire and smoke data to create proficient Machine Learning (ML) methods for various tasks, such as detection and monitoring. Although fire and smoke datasets play a critical role in training, evaluating, and testing advanced Deep Learning (DL) models, a comprehensive review of the existing datasets is still unexplored. For this purpose, we provide an in-depth review to systematically analyze and evaluate fire and smoke datasets collected over the past 20 years. We investigate the characteristics of each dataset, including type, size, format, collection methods, and geographical diversities. We also review and highlight the unique features of each dataset, such as imaging modalities (RGB, thermal, infrared) and their applicability for different fire management tasks (classification, segmentation, detection). Furthermore, we summarize the strengths and weaknesses of each dataset and discuss their potential for advancing research and technology in fire management. Ultimately, we conduct extensive experimental analyses across different datasets using several state-of-the-art algorithms, such as ResNet-50, DeepLab-V3, and YoloV8.

arXiv:2503.15865

Active management of battery degradation in wireless sensor network using deep reinforcement learning for group battery replacement

Wireless sensor networks (WSNs) have become a promising solution for structural health monitoring (SHM), especially in hard-to-reach or remote locations. Battery-powered WSNs offer various advantages over wired systems, however limited battery life has always been one of the biggest obstacles in practical use of the WSNs, regardless of energy harvesting methods. While various methods have been studied for battery health management, existing methods exclusively aim to extend lifetime of individual batteries, lacking a system level view. A consequence of applying such methods is that batteries in a WSN tend to fail at different times, posing significant difficulty on planning and scheduling of battery replacement trip. This study investigate a deep reinforcement learning (DRL) method for active battery degradation management by optimizing duty cycle of WSNs at the system level. This active management strategy effectively reduces earlier failure of battery individuals which enable group replacement without sacrificing WSN performances. A simulated environment based on a real-world WSN setup was developed to train a DRL agent and learn optimal duty cycle strategies. The performance of the strategy was validated in a long-term setup with various network sizes, demonstrating its efficiency and scalability.

arXiv:2503.16200

Notes on Correlation Stress Tests

This note outlines an approach to stress testing of covariance of financial time series, in the context of financial risk management. It discusses how the geodesic distance between covariance matrices implies a notion of plausibility of covariance stress tests. In this approach, correlation stress tests span a submanifold of constant determinant of the Fisher--Rao manifold of covariance matrices. A parsimonious geometrically invariant definition of arbitrarily large correlation stress tests is proposed, and a few examples are discussed.

arXiv:2503.15668

Model Risk Management for Generative AI In Financial Institutions

The success of OpenAI's ChatGPT in 2023 has spurred financial enterprises into exploring Generative AI applications to reduce costs or drive revenue within different lines of businesses in the Financial Industry. While these applications offer strong potential for efficiencies, they introduce new model risks, primarily hallucinations and toxicity. As highly regulated entities, financial enterprises (primarily large US banks) are obligated to enhance their model risk framework with additional testing and controls to ensure safe deployment of such applications. This paper outlines the key aspects for model risk management of generative AI model with a special emphasis on additional practices required in model validation.

arXiv:2503.15534

Systemic Risk Management via Maximum Independent Set in Extremal Dependence Networks

The failure of key financial institutions may accelerate risk contagion due to their interconnections within the system. In this paper, we propose a robust portfolio strategy to mitigate systemic risks during extreme events. We use the stock returns of key financial institutions as an indicator of their performance, apply extreme value theory to assess the extremal dependence among stocks of financial institutions, and construct a network model based on a threshold approach that captures extremal dependence. Our analysis reveals different dependence structures in the Chinese and U.S. financial systems. By applying the maximum independent set (MIS) from graph theory, we identify a subset of institutions with minimal extremal dependence, facilitating the construction of diversified portfolios resilient to risk contagion. We also compare the performance of our proposed portfolios with that of the market portfolios in the two economies.

arXiv:2503.16139

Aging-aware Energy Management for Residential Multi-Carrier Energy Systems

In the context of building electrification, the operation of distributed energy resources integrating multiple energy carriers (electricity, heat, mobility) poses a significant challenge due to the nonlinear device dynamics, uncertainty, and computational issues. As such, energy management systems seek to decide set points for the primary control layer in the best way possible. The objective is to minimize and balance operative costs (energy bills or asset degradation) with user requirements (mobility, heating, etc.). This paper presents a novel aging-aware day-ahead algorithm for electrified buildings. The proposed energy management algorithm incorporates physics-based battery aging models to enhance the operational performance, making explicit the trade-off between grid cost and battery degradation. The proposed day-ahead algorithm can either cut-down on grid costs or extend battery lifetime (electric vehicle or static packs). Moreover, it exploits the differences between cathode chemistries improving grid costs by 25\% when using LFP cells, with respect to NMC cells. Finally the performance using aged batteries is also enhanced, with respect to the benchmarks.

arXiv:2503.15394

Advancing MG Energy Management: A Rolling Horizon Optimization Framework for Three-Phase Unbalanced Networks Integrating Convex Formulations

Real-world three-phase microgrids face two interconnected challenges: 1. time-varying uncertainty from renewable generation and demand, and 2. persistent phase imbalances caused by uneven distributed energy resources DERs, load asymmetries, and grid faults. Conventional energy management systems fail to address these challenges holistically and static optimization methods lack adaptability to real-time fluctuations, while balanced three-phase models ignore critical asymmetries that degrade voltage stability and efficiency. This work introduces a dynamic rolling horizon optimization framework specifically designed for unbalanced three-phase microgrids. Unlike traditional two-stage stochastic approaches that fix decisions for the entire horizon, the rolling horizon algorithm iteratively updates decisions in response to real-time data. By solving a sequence of shorter optimization windows, each incorporating the latest system state and forecasts, the method achieves three key advantages: Adaptive Uncertainty Handling by continuously re plans operations to mitigate forecast errors. Phase Imbalance Correction by dynamically adjusts power flows across phases to minimize voltage deviations and losses caused by asymmetries, and computational Tractability, i.e., shorter optimization windows, combined with the mathematical mhodel, enable better decision making holding accuracy. For comparison purposes, we derive three optimization models: a nonlinear nonconvex model for high-fidelity offline planning, a convex quadratic approximation for day-ahead scheduling, and a linearized model to important for theoretical reasons such as decomposition algorithms.

arXiv:2503.14801

Towards Connected Smart Work Zones: Advancing Work Zone Management through Improved Connectivity

Work zones play a key role in road and highway maintenance but can lead to significant risks to both drivers and workers. Smart Work Zones (SWZs) have emerged as a potential solution, offering decision-makers real-time insights into the status of the work zone. By utilizing work zone barrels equipped with sensors and communication nodes, SWZs facilitate collecting and transmitting critical data, including location, traffic density, flow patterns, and worker proximity alerts. In collaboration with the Florida Department of Transportation (FDOT), this study addresses work zone barrel connectivity requirements while considering a cost-effective, low-power, and low-maintenance solution. While the broader project aimed to create a complete SWZ system for the localization of work zone barrels, this paper proposes a novel relay node selection algorithm integrated with Bluetooth Low Energy (BLE) technology to enhance network performance. The proposed algorithm enhances the communication network performance by selecting specific nodes as relay points, avoiding message flooding in the network. It demonstrates an improvement in message delivery rates, achieving up to a 40% increase over existing methods while ensuring balanced load distribution among nodes. Moreover, it maintains an 80% message delivery rate while minimizing power consumption, outperforming other approaches. This improvement in communication efficiency is critical, as it ensures the accurate transmission and delivery of vital work zone data, allowing for faster and more informed decisions to enhance work zone safety and management.

arXiv:2503.16191

Large Language Models for Water Distribution Systems Modeling and Decision-Making

The design, operations, and management of water distribution systems (WDS) involve complex mathematical models. These models are continually improving due to computational advancements, leading to better decision-making and more efficient WDS management. However, the significant time and effort required for modeling, programming, and analyzing results remain substantial challenges. Another issue is the professional burden, which confines the interaction with models, databases, and other sophisticated tools to a small group of experts, thereby causing non-technical stakeholders to depend on these experts or make decisions without modeling support. Furthermore, explaining model results is challenging even for experts, as it is often unclear which conditions cause the model to reach a certain state or recommend a specific policy. The recent advancements in Large Language Models (LLMs) open doors for a new stage in human-model interaction. This study proposes a framework of plain language interactions with hydraulic and water quality models based on LLM-EPANET architecture. This framework is tested with increasing levels of complexity of queries to study the ability of LLMs to interact with WDS models, run complex simulations, and report simulation results. The performance of the proposed framework is evaluated across several categories of queries and hyper-parameter configurations, demonstrating its potential to enhance decision-making processes in WDS management.

arXiv:2503.14543

Inteligencia Artificial para la conservación y uso sostenible de la biodiversidad, una visión desde Colombia (Artificial Intelligence for conservation and sustainable use of biodiversity, a view from Colombia)

The rise of artificial intelligence (AI) and the aggravating biodiversity crisis have resulted in a research area where AI-based computational methods are being developed to act as allies in conservation, and the sustainable use and management of natural resources. While important general guidelines have been established globally regarding the opportunities and challenges that this interdisciplinary research offers, it is essential to generate local reflections from the specific contexts and realities of each region. Hence, this document aims to analyze the scope of this research area from a perspective focused on Colombia and the Neotropics. In this paper, we summarize the main experiences and debates that took place at the Humboldt Institute between 2023 and 2024 in Colombia. To illustrate the variety of promising opportunities, we present current uses such as automatic species identification from images and recordings, species modeling, and in silico bioprospecting, among others. From the experiences described above, we highlight limitations, challenges, and opportunities for in order to successfully implementate AI in conservation efforts and sustainable management of biological resources in the Neotropics. The result aims to be a guide for researchers, decision makers, and biodiversity managers, facilitating the understanding of how artificial intelligence can be effectively integrated into conservation and sustainable use strategies. Furthermore, it also seeks to open a space for dialogue on the development of policies that promote the responsible and ethical adoption of AI in local contexts, ensuring that its benefits are harnessed without compromising biodiversity or the cultural and ecosystemic values inherent in Colombia and the Neotropics.