arXiv subjects

Alexandra Băicoianu

Publications and source records attributed to Alexandra Băicoianu.

5 recordsLinked to original sources

arXiv2026

Lake Detection and Water Quality Estimation in Sentinel-2 Data

With climate change and increasing human pressure on natural landscapes, inland water resources are becoming progressively scarcer, more vulnerable, and more difficult to manage sustainably. Reliable and automated methods for detecting, monitoring, and assessing surface water bodies are therefore of growing scientific and practical importance. In this paper, we investigate and compare three distinct machine learning architectures for water body identification and monitoring. Their performance is evaluated through quantitative metrics and real-world examples. Furthermore, a direct comparison with classical NDWI thresholding is conducted on a representative test image to highlight differences between data-driven and index-based approaches. This analysis allows us to identify the best-performing model in terms of accuracy, robustness, and practical applicability. Beyond detection, a major challenge for meaningful water quality assessment lies in the consistent and interpretable visualization of spectral water indices. Standard color mapping techniques are often inadequate or potentially misleading for environmental applications. To address this gap, we propose a suite of meaningful color schemes adapted for water quality indices, facilitating clearer interpretation, comparison, and decision-making for human users.

cs.LG↗

arXiv2026

Texture Regenerating and Grafting Using Genome-Driven Neural Cellular Automata

This study significantly advances multi-texture synthesis using Neural Cellular Automata (NCAs) by introducing a novel training methodology that enables robust self-regeneration of textures in damaged regions. This inherent healing mechanism, essential for dynamic and adaptive systems, extends beyond traditional computer graphics applications, highlighting the fundamental self-organizing properties of NCAs. Furthermore, we present a versatile grafting technique, enabling the seamless combination of distinct textures. This is achieved efficiently during the inference phase, without requiring specialized retraining, through precise initialization of the NCA's genome channels. Our findings demonstrate the generation of high-quality, complex textures with fluid transitions, showcasing a powerful and efficient paradigm for dynamic texture composition and self-repair in autonomous systems.

cs.NE↗

arXiv2024

Conformal Transformation of Kernels: A Geometric Perspective on Text Classification

In this article we investigate the effects of conformal transformations on kernel functions used in Support Vector Machines. Our focus lies in the task of text document categorization, which involves assigning each document to a particular category. We introduce a new Gaussian Cosine kernel alongside two conformal transformations. Building upon previous studies that demonstrated the efficacy of conformal transformations in increasing class separability on synthetic and low-dimensional datasets, we extend this analysis to the high-dimensional domain of text data. Our experiments, conducted on the Reuters dataset on two types of binary classification tasks, compare the performance of Linear, Gaussian, and Gaussian Cosine kernels against their conformally transformed counterparts. The findings indicate that conformal transformations can significantly improve kernel performance, particularly for sub-optimal kernels. Specifically, improvements were observed in 60% of the tested scenarios for the Linear kernel, 84% for the Gaussian kernel, and 80% for the Gaussian Cosine kernel. In light of these findings, it becomes clear that conformal transformations play a pivotal role in enhancing kernel performance, offering substantial benefits.

cs.LG↗

arXiv2024

Optimizing Intensive Database Tasks Through Caching Proxy Mechanisms

Web caching is essential for the World Wide Web, saving processing power, bandwidth, and reducing latency. Many proxy caching solutions focus on buffering data from the main server, neglecting cacheable information meant for server writes. Existing systems addressing this issue are often intrusive, requiring modifications to the main application for integration. We identify opportunities for enhancement in conventional caching proxies. This paper explores, designs, and implements a potential prototype for such an application. Our focus is on harnessing a faster bulk-data-write approach compared to single-data-write within the context of relational databases. If a (upload) request matches a specified cacheable URL, then the data will be extracted and buffered on the local disk for later bulk-write. In contrast with already existing caching proxies, Squid, for example, in a similar uploading scenario, the request would simply get redirected, leaving out potential gains such as minimized processing power, lower server load, and bandwidth. After prototyping and testing the suggested application against Squid, concerning data uploads with 1, 100, 1.000, ..., and 100.000 requests, we consistently observed query execution improvements ranging from 5 to 9 times. This enhancement was achieved through buffering and bulk-writing the data, the extent of which depended on the specific test conditions.

cs.DB↗

arXiv2024

Quantum Tunneling: From Theory to Error-Mitigated Quantum Simulation

Ever since the discussions about a possible quantum computer arised, quantum simulations have been at the forefront of possible utilities and the task of quantum simulations is one that promises quantum advantage. In recent years, simulations of large molecules through VQE or dynamics of many-body spin Hamiltonians may be possible, and even able to achieve useful results with the use of error mitigation techniques. Simulating smaller models is also important, and currently, in the NISQ (Noisy intermediate-scale quantum) era, it is easier and less prone to errors. This current study encompasses the theoretical background and the hardware aware circuit implementation of a quantum tunneling simulation. Specifically, this study presents the theoretical background needed for such implementation and highlights the main steps of development. Building on classic approaches of quantum tunneling simulations, this study improves the result of such simulations by employing error mitigation techniques (ZNE and REM) and uses them in conjunction with multiprogramming of the quantum chip for solving the hardware under-utilization problem that arises in such contexts. Moreover, we highlight the need for hardware-aware circuit implementations and discuss these considerations in detail to give an end-to-end workflow overview of quantum simulations.

quant-ph↗