Abstract
The growing demand for high-quality components in various industries, particularly in the automotive sector, requires advanced and reliable inspection methods to maintain competitive standards and support innovation. Manual quality inspection tasks are often inefficient and prone to errors due to their repetitive nature and subjectivity, which can lead to attention lapses and operator fatigue. The inspection of reflective aluminum parts presents additional challenges, as uncontrolled reflections and glare can obscure defects and reduce the reliability of conventional vision-based methods. Addressing these challenges requires optimized illumination strategies and robust image processing techniques to enhance defect visibility. This work presents the development of an automated optical inspection system for reflective parts, focusing on components made of high-pressure diecast aluminum used in the automotive industry. The reflective nature of these parts introduces challenges for defect detection, requiring optimized illumination and imaging methods. The system applies deep learning algorithms and uses dome light to achieve uniform illumination, enabling the detection of small defects on reflective surfaces. A collaborative robotic manipulator equipped with a gripper handles the parts during inspection, ensuring precise positioning and repeatability, which improves both the efficiency and effectiveness of the inspection process. A flow execution-based software platform integrates all system components, enabling seamless operation. The system was evaluated with Schmidt Light Metal Group using three custom datasets to detect surface porosities and inner wall defects post-machining. For surface porosity detection, YOLOv8-Mosaic, trained with cropped images to reduce background noise, achieved a recall value of 84.71% and was selected for implementation. Additionally, an endoscopic camera was used in a preliminary study to detect defects within the inner walls of holes. The industrial trials produced promising results, demonstrating the feasibility of implementing a vision-based automated inspection system in various industries. The system improves inspection accuracy and efficiency while reducing material waste and operator fatigue.

Abstract
The Digital Model concept of factory floor equipment allows simulation, visualization and processing, and the ability to communicate between the various workstations. The Digital Twin is the concept used for the digital representation of equipment on the factory floor, capable of collecting a set of data about the equipment and production, using physical sensors installed in the equipment. Within the scope of data visualization and processing, there is a need to manage information about parameters/conditions that the assembly line equipments must present to start a production order, or in a shift handover. This study proposes a paperless checklist to manage equipment information and monitor production ramp-up. The proposed solution is validated in a real-world industrial scenario, by comparing its suitability against the current paper-based approach to log information. Results show that the paperless checklist presents advantages over the current approach since it enables multi-access viewing and logging while maintaining a digital history of log changes for further analysis. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

Abstract
Lung cancer is a significant global health concern, and accurate classification of lung nodules plays a crucial role in its early detection and treatment. This paper evaluates and compares the performance of Vision Transformer (ViT) and Convolutional Neural Network (CNN) models for lung nodule classification using the Pylung tool proposed in this work. The study aims to address the lack of research on ViT in lung nodule classification and proposes ViT as an alternative to CNN. The Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset is utilized for training and evaluation. The Pylung tool is employed for dataset preprocessing and comparison of models. Three models, ViT, VGG16, and ResNet50, are analyzed, and their hyperparameters are optimized using Optuna. The results show that ViT achieves the highest accuracy (99.06%) in nodule classification compared to VGG16 (98.71%) and ResNet50 (98.46%). The study contributes by introducing ViT as a model for lung nodule classification, presenting the Pylung tool for model comparison, and suggesting further investigations to improve the accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Abstract
This study focuses on investigating different CNN architectures and assessing their effectiveness in classifying Diabetic Retinopathy, a diabetes-associated disease that ranks among the primary causes of adult blindness. However, early detection can significantly prevent its debilitating consequences. While regular screening is advised for diabetic patients, limited access to specialized medical professionals can hinder its implementation. To address this challenge, deep learning techniques provide promising solutions, primarily through their application in the analysis of fundus retina images for diagnosis. Several CNN architectures, including MobileNetV2, VGG16, VGG19, InceptionV3, InceptionResNetV2, Xception, DenseNet121, ResNet50, ResNet50V2, and EfficientNet (ranging from EfficientNetB0 to EfficientNetB6), were implemented to assess and analyze their performance in classifying Diabetic Retinopathy. The dataset comprised 3662 Fundus retina images. Prior to training, the networks underwent pre-training using the ImageNet database, with a Gaussian filter applied to the images as a preprocessing step. As a result, the Efficient-Net stands out for achieving the best performance results with a good balance between model size and computational efficiency. By utilizing the EfficientNetB2 network, a model was trained with an accuracy of 85% and a screening capability of 98% for Diabetic Retinopathy. This model holds the potential to be implemented during the screening stages of Diabetic Retinopathy, aiding in the early identification of individuals at risk. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

Abstract
Prostate cancer is one of the most common types of cancer in men. The ISUP grade and Gleason Score are terms related to the classification of this cancer based on the histological characteristics of the tissues examined in a biopsy. This paper explains an approach that utilizes and evaluates pre-trained models such as ResNet-50, VGG19, and InceptionV3, regarding their ability to automatically classify prostate cancer and its severity based on images and masks annotated with ISUP grades and Gleason Scores. At the end of the training, the performance of each trained model is presented, as well as the comparison between the original and predicted data. This comparison aims to understand if this approach can indeed be used for a more automated classification of prostate cancer. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

Abstract