CRIS

Permanent URI for this communityhttps://cris-udd.scimago.es/handle/123456789/1

Browse

Settings

Start date: 2024Subject: search.filters.subject.Convolutional Neural Networks

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Implementation of Convolutional Neural Networks for Object Detection in Robotic Pick-and-Place Processes
    (Springer Nature Switzerland, 2026)
    Villazón, Renato
    ;
    Pilco, Andrea
    ;
    Prado, Alvaro Javier
    ;
    Moya, Viviana
    ;
    Chicaiza Claudio, Fernando  
    Pick-and-place (P&P) tasks in robotic applications have attracted considerable interest for several years. As these are repetitive tasks that are performed continuously and uninterruptedly, any slight improvement in the efficiency of this process results in a significant increase of productivity. In this work, we propose improving a pick-and-place task performed by two Dobot Magician educational manipulator robots alongside a conveyor belt. This system natively incorporates a hardware-based color sensor that allows the robot to identify and classify objects on a conveyor belt, organizing and palletizing them in specific columns according to their color characteristics. However, the robot spends time picking up the objects, placing them on the sensor, and then beginning palletization. In this work, we propose using the Faster R-CNN object detection model with ResNet-50 for feature extraction as an external and independent vision system to streamline and reduce the time losses associated with the hardware-based color sensor tasks. The implemented model achieved a mean Average Precision (mAP) of 68.0% during validation and 65.32% in real-world operation. The system accurately detects all key components involved in the task, including robotic arms, end effectors, the conveyor belt, the color sensor, and the colored blocks (red, green, and blue). When compared to the hardware-based color sensor method, the proposed approach reduced the total processing time from 249.31 s to 196.65 s, representing an improvement of 52.66 s, or approximately 21.12% in overall efficiency. This demonstrates the potential and promising results of using deep learning models in pick-and-place-related applications.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Development of a Convolutional Neural Network for Detection of Ovarian Cancer Based on Computed Tomography Images
    (2024)
    Gabriela Narvaez-Chunillo
    ;
    Ronny Ordoñez-Sanchez
    ;
    Lizbeth Ortiz-Vinueza
    ;
    Diego Almeida-Galárraga
    ;
    Fernando Villalba-Meneses
    Ovarian cancer is one of the most frequent gynecologic malignancies in women, but it is often detected in late stage, leaving patients with little time to follow a successful therapy. Specialists have opted to use computer-aided diagnosis (CAD) for the detection of ovarian cancer through the analysis of computed tomography (CT) images, in which the professional examines the size, shape and different characteristics that enable a precise diagnosis in the ovary. This present project purposes a Convolutional Neural Network (CNN) which consist on four convolutional layers; including two pooling layer and two fully-connected layer. The cancerous ovaries images is selected from the Cancer Imaging Achive dataset for training and validation of the model. Moreover, the training of the CNN contain filters to ensure that all of the images are the same dimensions and pixel size. The testing results from the training of the images showed that the proposed model obtained a range of accuracy that goes from 90.0% to the best of the cases 98.85%. The variables obtained like the data of the pressure and loss of the training were compared with those of the validation, allowing for the determination of a successful CNN training.
      15