Ayala-Chauvin, Manuel Ignacio
Thumbnail Image
Preferred name
Ayala-Chauvin, Manuel Ignacio
Main Affiliation
Ambato
Email
mayala@uti.edu.ec
ORCID
Scopus Author ID
57215428914

Research Output
Now showing 1 - 4 of 4
No Thumbnail Available
Publication

U-Net Models for Breast Cancer Detection: Improving Diagnostic Accuracy and Specificity

2024 , Dayanara Yánez-Arcos , Ayala-Chauvin, Manuel Ignacio , Elena Blanco-Romero

Breast cancer remains a critical global health issue, necessitating continuous research and innovative approaches for diagnosis, treatment, and prevention. This study evaluates the effectiveness of U -Net models in enhancing diagnostic precision and efficiency using real hospital samples. We aim to improve key diagnostic metrics such as accuracy, sensitivity, and specificity through the application of U-Net models. Our image classification model, tailored for 256 × 256 × 3 input images, excels in detecting and categorizing tumor cells. The architecture begins with initial convolutional layers featuring 64 filters, progresses to layers with 128 filters, and includes a Dropout layer to prevent overfitting. The deep network for object detection utilizes both region proposal and regression/classification approaches, achieving 92.27% confidence and 100% accuracy. Additionally, our deep learning algorithms accurately segment nuclei in histopathological images, employing a clustering strategy that delivers 88.81% confidence and 100% accuracy. Visual results demonstrate precise tumor cell localization and prediction confidence. Performance metrics from ten experimental runs indicate average confidence levels between 74.19% and 92.31%, with 90.0% accuracy and specificity in benign analysis. The model's ability to classify non-carcinomas versus carcinomas achieved an AUC of 0.78, illustrating its effective differentiation between classes.

View
No Thumbnail Available
Publication

Performance and Real-World Variability of Predictive Maintenance Models for Vehicle Fleets

2024 , Avilés-Castillo, Fátima , Dayanara Yánez-Arcos , Ayala-Chauvin, Manuel Ignacio , Elena Blanco-Romero

This study presents a comprehensive evaluation of predictive maintenance models for vehicle fleets, detailing a sequence of systematic steps to ensure model performance and address real-world variability. The process begins with database creation and data preprocessing, where relevant maintenance records are filtered, and datetime columns are converted to facilitate time-based calculations. Grouping and aggregation techniques are then applied to count occurrences of specific maintenance activities and identify common failure types. For model training, we define a neural network architecture comprising dense and dropout layers to mitigate overfitting, compile the model with suitable loss functions and optimizers, and train it using the prepared data. The trained model, along with the scaler and encoder, is saved for future use. To augment the dataset, synthetic data is generated using the Faker library and random distributions, with added noise to mimic real-world variability. Preprocessing steps are reapplied to this synthetic data to ensure consistency. By implementing this neural network, we achieved a sensitivity of 0.93 and an ROC of 0.71. Following these detailed steps, we develop a robust predictive maintenance model that effectively identifies failures and non-failures, ultimately enhancing the reliability and efficiency of vehicle fleet management.

View
No Thumbnail Available
Publication

Predictive Maintenance in Industrial Robotics Using Big Data: Techniques, Challenges, and Opportunities

2024 , Ayala-Chauvin, Manuel Ignacio , Avilés-Castillo, Fátima , Dayanara Yánez-Arcos , Buele, Jorge

In industrial robotics, predictive maintenance is important to improve efficiency and reduce costs, addressing early detection and diagnosis of failures. The use of Big Data allows us to identify patterns and trends that at first glance are complex. This review examines research on the application of big data in predictive maintenance of industrial robots, which use advanced techniques such as cloud-based architectures, filtering algorithms, and machine learning. The review methodology included an analysis of the big data techniques used, the challenges identified, and the opportunities presented. The results show significant improvements in the accuracy of predictions and fault diagnoses. Key anomaly drivers were identified that improved production performance and enabled accurate fault identification and reduced downtime in industrial robots. Despite the benefits, challenges remain in data security and communications latency, underscoring the need to develop innovative algorithms and techniques to balance computing load and minimize delays. The continuous evolution of these techniques promises to improve the failure management capacity in industrial robotics, thus optimizing the operability and efficiency of robotic systems.

View
No Thumbnail Available
Publication

U-Net Models for Breast Cancer Detection: Improving Diagnostic Accuracy and Specificity

2024 , Dayanara Yánez-Arcos , Ayala-Chauvin, Manuel Ignacio , Elena Blanco-Romero

Breast cancer remains a critical global health issue, necessitating continuous research and innovative approaches for diagnosis, treatment, and prevention. This study evaluates the effectiveness of U -Net models in enhancing diagnostic precision and efficiency using real hospital samples. We aim to improve key diagnostic metrics such as accuracy, sensitivity, and specificity through the application of U-Net models. Our image classification model, tailored for 256 × 256 × 3 input images, excels in detecting and categorizing tumor cells. The architecture begins with initial convolutional layers featuring 64 filters, progresses to layers with 128 filters, and includes a Dropout layer to prevent overfitting. The deep network for object detection utilizes both region proposal and regression/classification approaches, achieving 92.27% confidence and 100% accuracy. Additionally, our deep learning algorithms accurately segment nuclei in histopathological images, employing a clustering strategy that delivers 88.81% confidence and 100% accuracy. Visual results demonstrate precise tumor cell localization and prediction confidence. Performance metrics from ten experimental runs indicate average confidence levels between 74.19% and 92.31%, with 90.0% accuracy and specificity in benign analysis. The model's ability to classify non-carcinomas versus carcinomas achieved an AUC of 0.78, illustrating its effective differentiation between classes

View