Skip to main content

MEJORANDO LA EXPERIENCIA DEL USUARIO DE CIENCIA DE DATOS CON TECNICAS DE INTELIGENCIA COMPUTACIONAL

PID2020-115832GB-I00

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2020
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE CORDOBA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Helvia. Repositorio Institucional de la Universidad de Córdoba
Publication Artículo científico (JournalArticle)

A framework to build accurate Convolutional Neural Network models for melanoma diagnosis

  • Pérez Perdomo, Eduardo
  • Ventura Soto, S.
In the past few years, Convolutional Neural Networks have achieved performance levels similar to those achieved by dermatologists. However, the diagnosis of melanoma remains a challenging task, mainly due to the high levels of inter and intra-class variability present in images of moles. With the aim of new methods for an effective melanoma diagnosis, a new framework is proposed. The training process is guided by an expert within an active learning approach where the architectures implicitly learn about the complexity of individual images through query strategies, which allows us to adjust the training process and achieve better performance. In addition, we propose a batch-based query strategy that enables a more stable and faster training process. Besides, the framework leverages segmentation, data augmentation and transfer learning to enhance melanoma diagnosis. The framework is composed by several specialized blocks, which allow us to measure how the diagnosis is improved after each step. In this sense, blocks could be customized and do not depend on specific models. An extensive experimental study was conducted on 16 skin image datasets, where five state-of-the-art models were significantly outperformed. This study corroborated that new active learning query strategies can be employed to effectively train neural networks architectures for the diagnosis of melanoma, achieving 182% better predictive performance in Xception, and an overall 11% and 20% better predictive performance in dermoscopic and non-dermoscopic images, respectively. It is worth mentioning that the informativeness value of each image is shown, which leads to identify the hardest images for the predictive models. Finally, the proposal required 2% of the total training time, and needed 61% less training epochs.
Helvia. Repositorio Institucional de la Universidad de Córdoba
Publication Artículo científico (JournalArticle)

Design of novel intelligent electronic trap for early detection and monitoring of tomato crops pest Tuta Absoluta using Deep learning

  • Abid Alasady, Yaser M.
  • Pérez Perdomo, Eduardo
  • Ventura Soto, S.
To control insect pests and reduce the destruction of agricultural crops, the process of detection and monitoring of pests is an urgent need at present time. Due to the tremendous development in technology, the traditional methods used in laboratories considered a waste of time and human efforts. In this research, a new data set collected and published for the first time, novel electronic trap designed with intelligent system to detect pests in tomato crop, and monitor the spread of the pest periodically and continuously based on the collected dataset. As the designed intelligent system firstly consists of a novel trap designed in a way that contains six colored sticky traps to catch insects continuously, controlled by L293D IC to rotate the motor, a digital camera used to provide the system with real images at periodic intervals. To detect pest, the (YOLOv11, YOLOv9, YOLOv8 and YOLOv5) used for this purpose. The Tuta Absoluta pest used for the detection and monitoring process of the designed novel intelligent system. The results used in the system; the precision was 95.9%, recall was 92.5%, Mean Average Precision (mAP 0.5) was 94% and F1 score was 94% and the results were promising. As compared to other models of (YOLOv11, YOLOv9, YOLOv8 and YOLOv5), the YOLOv5x shows that its higher results than other models. This system is easy to use and accurate in providing the information required monitoring the spread of the insect pest, therefore it could use in modern agricultural applications.
Helvia. Repositorio Institucional de la Universidad de Córdoba
Publication Contribución de congreso (ConferenceOutput)

Multi-view Deep Neural Networks for multiclass skin lesion diagnosis

  • Pérez, Eduardo
  • Ventura Soto, S.
Early diagnosis is still the best method to face skin cancer. The diagnosis of skin lesions remains as a challenge for physicians and researchers. In the past few years, it has benefited from computer-aided diagnosis methods that successfully apply classic Machine Learning techniques and more recently Convolutional Neural Networks. This work is aimed at discovering architectures that best fuse clinical records and medical images for the diagnosis of skin lesions. As a result, a genetic algorithm is designed in order to select how to combine such information and the main details of the new architecture. The architecture is able to cope with multiple inputs and learn multiple outputs, proving flexibility by sharing network parameters, which implicitly mitigates the overfitting of the model. An extensive experimental study was conducted on the well-known ISIC2019 dataset, where the models were trained with a total of 72,106 images and meta-data, including the augmented images. The proposal outperformed the baseline state-of-the-art model while diagnosing from eight skin lesion categories. Furthermore, the discovered architecture achieved 85%, 94%, and 84% of recall score when diagnosing malignant lesions - melanoma, basal cell carcinoma, and squamous cell carcinoma, respectively. Finally, the results showed the suitability of the proposed genetic algorithm, which was able to automatically build a multimodal fusion architecture for the diagnosis of skin lesions.
Helvia. Repositorio Institucional de la Universidad de Córdoba
Publication Artículo científico (JournalArticle)

Initialization of Feature Selection Search for Classification

  • Luque Rodríguez, María
  • Molina-Baena, José
  • Jiménez-Vílchez, Alfonso
  • Arauzo Azofra, Antonio
Selecting the best features in a dataset improves accuracy and efficiency of classifiers in a learning process. Datasets generally have more features than necessary, some of them being irrelevant or redundant to others. For this reason, numerous feature selection methods have been developed, in which different evaluation functions and measures are applied. This paper proposes the systematic application of individual feature evaluation methods to initialize search-based feature subset selection methods. An exhaustive review of the starting methods used by genetic algorithms from 2014 to 2020 has been carried out. Subsequently, an in-depth empirical study has been carried out evaluating the proposal for different search-based feature selection methods (Sequential forward and backward selection, Las Vegas filter and wrapper, Simulated Annealing and Genetic Algorithms). Since the computation time is reduced and the classification accuracy with the selected features is improved, the initialization of feature selection proposed in this work is proved to be worth considering while designing any feature selection algorithms.