scholarly journals Sistema basado en conocimiento para la obtención de flujos de trabajo aplicables al realce de imágenes digitales de archivos históricos

2018 ◽  
Vol 2 (11) ◽  
Author(s):  
Yuniel Guzmán Bazán ◽  
Juan Valentín Lorenzo Ginori ◽  
Julio Cedeño Ferrín
Keyword(s):  
Digital Images ◽  
Pearson Correlation ◽  
Case Based Reasoning ◽  
Support Tool ◽  
Preventive Conservation ◽  
Restoration Process ◽  
Reasoning System ◽  
Digital Format ◽  
Scanned Images ◽  
Case Based

Hoy en día existe un creciente deterioro en los documentos custodiados en las instituciones archivísticas cubanas. La manipulación de los investigadores, las manchas, huecos y la humedad, han provocado que sea poco legible el contenido de estos documentos. Por tal razón, se trabaja sobre su vertimiento a formato digital como medida de conservación preventiva. Las imágenes resultado de la digitalización requieren una restauración que mejore su legibilidad. Con tal propósito se creó la aplicación DocLux. Actualmente el proceso de restauración no es efectivo. Los especialista de los Archivos Históricos deben seleccionar el flujo de trabajo (transformaciones y parámetros) necesario para la restauración de cada documento digitalizado. La inexperiencia de estos especialistas en procesamiento de imágenes digitales afecta la productividad de la restauración. En este trabajo se presenta una herramienta de apoyo para los especialistas de los Archivos Históricos con el objetivo de asistirlos en el proceso de restauración de las imágenes digitales. La herramienta recomienda el flujo de trabajo necesario para restaurar las imágenes digitalizadas. La parte central de la herramienta la constituye un sistema de razonamiento basado en casos y como técnica de extracción de características de imágenes el histograma de color. La recuperación de los casos más similares se realizó aplicando el coeficiente de correlación de Pearson. Las pruebas realizadas mostraron que con la herramienta propuesta se disminuye el tiempo necesario para restaurar las imágenes.   Palabras Claves: Realce de imágenes digitales, razonamiento basado en casos, histogramas de color, instituciones archivísticas, flujo de trabajo Abstract: Enhancement of digital images, case-based reasoning, color histograms, archival institutions, workflow Nowadays, there is an increasing deterioration in documents held in Cuban archival institutions. The handling of the researchers, stains, holes and humidity have turned the content of this documents to be unreadable. For this reason, it has being working on their migration into digital format as a measure of preventive conservation. The result of the scan images requires a restoration to improve readability. To this end, the Doclux application was created. Currently the restoration process is not effective. The specialists of the Archives must select the workflow (transformations and parameters) necessary for the restoration of each scanned document. The inexperience of these specialists on digital image processing affects the productivity of the restoration. This paper presents a support tool for specialists of the Archives, in order to assist in the restoration process of digital images. The tool recommends the workflow necessary to restore the scanned images. The central part of the tool is constituted by a case based reasoning system and the color histogram as feature images extraction technique. The recovery of the most similar cases was performed using the Pearson correlation coefficient. Tests showed that with the proposed tool, the time to restore the images decreases.

scholarly journals Using extended siamese networks to provide decision support in aquaculture operations

2021 ◽  
Author(s):  
Bjørn Magnus Mathisen ◽  
Kerstin Bach ◽  
Agnar Aamodt
Keyword(s):  
Neural Networks ◽  
Decision Support ◽  
Similar Case ◽  
Decision Makers ◽  
Similarity Function ◽  
Case Based Reasoning ◽  
Similarity Learning ◽  
Reasoning System ◽  
Siamese Networks ◽  
Case Based

AbstractAquaculture as an industry is quickly expanding. As a result, new aquaculture sites are being established at more exposed locations previously deemed unfit because they are more difficult and resource demanding to safely operate than are traditional sites. To help the industry deal with these challenges, we have developed a decision support system to support decision makers in establishing better plans and make decisions that facilitate operating these sites in an optimal manner. We propose a case-based reasoning system called aquaculture case-based reasoning (AQCBR), which is able to predict the success of an aquaculture operation at a specific site, based on previously applied and recorded cases. In particular, AQCBR is trained to learn a similarity function between recorded operational situations/cases and use the most similar case to provide explanation-by-example information for its predictions. The novelty of AQCBR is that it uses extended Siamese neural networks to learn the similarity between cases. Our extensive experimental evaluation shows that extended Siamese neural networks outperform state-of-the-art methods for similarity learning in this task, demonstrating the effectiveness and the feasibility of our approach.

A Case Based Reasoning System For Recommendation Of Restaurant In Jimbaran Using K-Nearest Neighbor

2020 ◽  
Vol 9 (2) ◽  
pp. 267
Author(s):  
I Gede Teguh Mahardika ◽  
I Wayan Supriana
Keyword(s):  
Recommendation System ◽  
Nearest Neighbor ◽  
Case Based Reasoning ◽  
Retrieval Process ◽  
K Nearest Neighbor ◽  
Reasoning System ◽  
Human Ability ◽  
And Function ◽  
Case Based ◽  
Selection Of

Culinary is one of the favorite businesses today. The number of considerations to choose a restaurant or place to visit becomes one of the factors that is difficult to determine the restaurant or place to eat. To get the desired place to eat advice, one needs a recommendation system. Decisions made by the recommendation system can be used as a reference to determine the choice of restaurants. One method that can be used to build a recommendation system is Case Based Reasoning. The Case Based Reasoning (CBR) method mimics human ability to solve a problem or cases. The retrieval process is the most important stage, because at this stage the search for a solution for a new case is carried out. The study used the K-Nearest Neighbor method to find closeness between new cases and case bases. With the selection of features used as domains in the system, the results of recommendations presented can be more suggestive and accurate. The system successfully provides complex recommendations based on the type and type of food entered by the user. Based on blackbox testing, the system has features that can be used and function properly according to the purpose of creating the system.

A Hierarchical Case-Based Reasoning System for Quality Design

2010 ◽  
Vol 20-23 ◽  
pp. 1015-1020
Author(s):  
Cai Yan Liu ◽  
You Fa Sun
Keyword(s):  
High Efficiency ◽  
Low Cost ◽  
Case Based Reasoning ◽  
Retrieval Accuracy ◽  
Reasoning System ◽  
Quality Specifications ◽  
Computation Formula ◽  
Quality Design ◽  
Similarity Computation ◽  
Case Based

Quality design means designing quality specifications and processing specifications of products with low cost and high efficiency. This paper presents a hierarchical case-based reasoning approach for quality design. The structure and expression of case-base, the hierarchical case retrieval algorithms and similarity computation formula between cases are all studied. Such a hierarchical case-based reasoning method will greatly improve the retrieval accuracy and efficiency.

Identification of Raman spectra through a case-based reasoning system: application to artistic pigments

2011 ◽  
Vol 42 (7) ◽  
pp. 1553-1561 ◽  
Author(s):  
M. Castanys ◽  
R. Perez-Pueyo ◽  
M. J. Soneira ◽  
E. Golobardes ◽  
A. Fornells
Keyword(s):  
Raman Spectra ◽  
System Application ◽  
Case Based Reasoning ◽  
Reasoning System ◽  
Case Based
Sign in / Sign up

Export Citation Format

Share Document