ABAndré Ricardo Backes

André Ricardo Backes

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


André Ricardo Backes has a total of 89 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Efficient speech denoising using CleanUNet optimized with Mamba and hybrid spectral loss

    by da Silva, Matheus Vieira, João Fernando Mari, André Ricardo Backes

    Speech enhancement aims to recover clean speech from signals degraded by noise and adverse acoustic conditions, such as background interference and echo. CleanUNet has emerged as an effective solution for causal speech denoising, but its high computational demands limit deployment on resource-constrained devices. In this work, we propose an optimized version of CleanUNet that significantly reduces model complexity while maintaining competitive performance. We replace the original Transformer bottleneck with a Mamba module, which offers efficient sequence modeling with linear time complexity. Additional architectural improvements include batch normalization, lightweight channel attention, alternative activation functions, and a novel hybrid loss function that combines Short-Time Fourier Transform and Wavelet-based components. Our best models achieved up to 86% parameter reduction relative to the original CleanUNet baseline with minimal performance degradation, and an ultralight version reduced parameters by up to 98% while still delivering competitive results in terms of Perceptual Evaluation of Speech Quality (PESQ) and Short-Time Objective Intelligibility (STOI). A comprehensive Pareto analysis illustrates the trade-offs between model size and speech quality, providing a range of configurations suited for different application scenarios, including real-time and embedded environments.

  • Open Access

    Ensemble of Handcrafted and Learned Features using a Lightweight CNN for Colorectal Cancer Classification

    by Larissa Ferreira Rodrigues Moreira, André Ricardo Backes

    Colorectal cancer (CRC) is one of the highest incident cancers in the world. The late-stage diagnosis plays a pivotal role in the mortality rate, making CRC the second leading cause of cancer-related deaths. Its diagnosis is based on the analysis of histological images acquired from a biopsy, a time-consuming and prone to errors task. Over the years, many deep learning and computer vision approaches have been proposed to automatize such a task, reducing the need for human specialists. To contribute to this area of research, we proposed an ensemble that combines a Lightweight CNN and handcrafted color texture features commonly used in literature. We investigated how different texture methods impact the performance of the ensemble in an important multi-class problem composed of eight types of tissues. Our ensemble obtained 99.63% accuracy, surpassing state of the art methods and deeper CNNs, and 99.63% F1 score, showing a good balance between precision and recall.


  • Open Access

    Semantic Segmentation of Coffee Regions From Satellite Images Using Deep Learning

    by João Marcelo Ribeiro, Vitor Augusto Negrão de Assis, Lais Bueno Palos, Jorge Otávio de Souza Nogueira, Jhonathas Emiliano Candido, André Ricardo Backes

    Coffee is one of the main agricultural products exported by Brazil, with Minas Gerais standing out as the largest producer and responsible for a significant portion of the country's production. Due to its importance, this work investigates various Convolutional Neural Networks (CNNs) for mapping coffee plantation areas in the municipality of Muzambinho, MG. Using satellite images, we evaluated four semantic segmentation network architectures: FCN, MA-NET, SegNet, and DeepLabV3. Experiments using a dataset with 100 satellite images demonstrated that the FCN and MA-NET networks achieve better performance in identifying crops than SegNet and DeepLabV3. The latter, however, presented generalization challenges in the test set, indicating sensitivity to variations in lighting and shading. The study highlights the potential of artificial intelligence combined with remote sensing to improve agricultural management, and the need for more robust and diversified datasets to optimize the generalization and robustness of the models in real conditions.


  • Open Access

    Combining Complex Networks and Multi-level Local Binary Patterns for Texture Analysis

    by André Ricardo Backes

    This study presents a novel approach to texture analysis that combines Complex Network Texture Descriptors (CNTD) with the Local Binary Pattern (LBP) technique. By generating "pattern images" through the application of LBP to the original texture image, the method introduces new sources of information that are further explored via CNTD method. We employed Particle Swarm Optimization (PSO) to investigate various combinations of these LBP patterns and descriptors and compared our results across three benchmark datasets. The proposed approach achieved accuracy rates of 99.54%, 99.88%, and 97.86% on the Vistex, Brodatz, and USPTex databases, respectively. These results highlight the effectiveness of the hybrid strategy in producing a highly discriminative feature vector for robust texture classification.

  • Open Access

    Cross-Validation Deep Learning for Breast Cancer Detection Using DMR-IR Infrared Images

    by Renata dos Santos Melo, Henrique Coelho Fernandes, André Ricardo Backes

    Breast cancer detection is a global health priority. While traditional methods have limitations, infrared thermography offers a promising, non-invasive alternative by detecting subtle thermal changes that can indicate tumors. This paper assessed five pre-trained Convolutional Neural Networks (CNNs) for breast cancer detection using DMR-IR thermal images, employing a 5-fold cross-validation. Among the tested models, ResNet50 achieved the best overall performance, with the highest average accuracy (92.79%), precision (95.00%), specificity (98.67%), sensitivity (72.00%), and F1-score (79.43%). The model was trained using raw thermal images from three anatomical views (frontal, lateral 90°, and lateral 45°), totaling five images per patient, an approach still uncommon in the literature. These results highlight ResNet50's strong potential for reliable and clinically applicable breast cancer detection using thermography.

  • Open Access

    PSO-based Client Selection to Improve Medical Image Classification in Federated Learning

    by Leonardo Gabriel Ferreira Rodrigues, Larissa Ferreira Rodrigues Moreira, Rodrigo Moreira, André Ricardo Backes

    Federated Learning (FL) offers an effective approach to enable collaborative model training across decentralized medical institutions while preserving patient privacy. However, FL faces challenges related to data heterogeneity and inefficient client participation issues. In this study, we introduce a novel client selection strategy based on Particle Swarm Optimization (PSO) to improve medical image classification in federated settings. Our method dynamically selects informative clients by evaluating their contributions to the global model, which reduces communication overhead and supports faster convergence. We performed experiments using three publicly available medical imaging datasets, Biglycan, ALL-IDB, and LC25000, focusing on binary classification tasks. The results show that the PSO-based approach improves performance over random client selection across all evaluated scenarios, with gains in accuracy, recall, precision, and F1-Score, even when selecting fewer clients. These findings indicate that incorporating PSO into FL frameworks helps address challenges related to data heterogeneity and communication efficiency while maintaining classification performance and privacy preservation.


  • Evaluating Architecture and Encoder Combinations for Cloud Segmentation in Satellite Images

    by Leandro Henrique Furtado Pinto Silva, Mauricio Cunha Escarpinati, André Ricardo Backes, João Fernando Mari

  • Open Access

    Generalizable Hyperparameter Optimization for Federated Learning on Non-IID Cancer Images

    by Elisa Gonçalves Ribeiro, Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira, André Ricardo Backes

    Deep learning for cancer histopathology training conflicts with privacy constraints in clinical settings. Federated Learning (FL) mitigates this by keeping data local; however, its performance depends on hyperparameter choices under non-independent and identically distributed (non-IID) client datasets. This paper examined whether hyperparameters optimized on one cancer imaging dataset generalized across non-IID federated scenarios. We considered binary histopathology tasks for ovarian and colorectal cancers. We perform centralized Bayesian hyperparameter optimization and transfer dataset-specific optima to the non-IID FL setup. The main contribution of this study is the introduction of a simple cross-dataset aggregation heuristic by combining configurations by averaging the learning rates and considering the modal optimizers and batch sizes. This combined configuration achieves a competitive classification performance.