CRIS

Permanent URI for this communityhttps://investigadores.udd.cl/handle/123456789/1

Browse

Settings

Author: search.filters.author.José GarcíaSubject: search.filters.subject.machine learning

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Relevance of Machine Learning Techniques in Water Infrastructure Integrity and Quality: A Review Powered by Natural Language Processing
    (2023)
    José García
    ;
    LEIVA ARAOS, ANDRÉS
    ;
    Emerson Diaz-Saavedra
    ;
    Paola Moraga
    ;
    Hernan Pinto
    Water infrastructure integrity, quality, and distribution are fundamental for public health, environmental sustainability, economic development, and climate change resilience. Ensuring the robustness and quality of water infrastructure is pivotal for sectors like agriculture, industry, and energy production. Machine learning (ML) offers potential for bolstering water infrastructure integrity and quality by analyzing extensive data from sensors and other sources, optimizing treatment protocols, minimizing water losses, and improving distribution methods. This study delves into ML applications in water infrastructure integrity and quality by analyzing English-language articles from 2015 onward, compiling a total of 1087 articles. Initially, a natural language processing approach centered on topic modeling was adopted to classify salient topics. From each identified topic, key terms were extracted and utilized in a semi-automatic selection process, pinpointing the most relevant articles for further scrutiny, while unsupervised ML algorithms can assist in extracting themes from the documents, generating meaningful topics often requires intricate hyperparameter adjustments. Leveraging the Bidirectional Encoder Representations from Transformers (BERTopic) enhanced the study’s contextual comprehension in topic modeling. This semi-automatic methodology for bibliographic exploration begins with a broad topic categorization, advancing to an exhaustive analysis of each topic. The insights drawn underscore ML’s instrumental role in enhancing water infrastructure’s integrity and quality, suggesting promising future research directions. Specifically, the study has identified four key areas where ML has been applied to water management: (1) advancements in the detection of water contaminants and soil erosion; (2) forecasting of water levels; (3) advanced techniques for leak detection in water networks; and (4) evaluation of water quality and potability. These findings underscore the transformative impact of ML on water infrastructure and suggest promising paths for continued investigation.
    Scopus© Citations 12  1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Exploring Initialization Strategies for Metaheuristic Optimization: Case Study of the Set-Union Knapsack Problem
    (2023)
    José García
    ;
    Andres Leiva-Araos
    ;
    Broderick Crawford
    ;
    Ricardo Soto  
    ;
    Hernan Pinto
    In recent years, metaheuristic methods have shown remarkable efficacy in resolving complex combinatorial challenges across a broad spectrum of fields. Nevertheless, the escalating complexity of these problems necessitates the continuous development of innovative techniques to enhance the performance and reliability of these methods. This paper aims to contribute to this endeavor by examining the impact of solution initialization methods on the performance of a hybrid algorithm applied to the set union knapsack problem (SUKP). Three distinct solution initialization methods, random, greedy, and weighted, have been proposed and evaluated. These have been integrated within a sine cosine algorithm employing k-means as a binarization procedure. Through testing on medium- and large-sized SUKP instances, the study reveals that the solution initialization strategy influences the algorithm’s performance, with the weighted method consistently outperforming the other two. Additionally, the obtained results were benchmarked against various metaheuristics that have previously solved SUKP, showing favorable performance in this comparison.
      32Scopus© Citations 4