Daniella Lúmara Peres

Daniella Lúmara Peres

Auto-generated profile, based on publicly available information

Daniella Lúmara Peres

Nuclear and Energy Research Institute University of so Paulo,Center for Lasers and Applications,So Paulo,Brazil

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 November 2024
Verified
Conference Paper
Closed access
DPDaniella Lúmara Peres
Daniella Lúmara Peres
GGGleice Germano
Gleice Germano
DSDaniela Silva
Daniela Silva
LBLuciano Bachmann
Luciano Bachmann
LMLeandro Luongo Matos
Leandro Luongo Matos
Denise Maria ZezellDenise Maria Zezell
Denise Maria Zezell
Early detection and diagnosis of oral squamous cell carcinoma (OSCC) are essential for improving patient outcomes. This study presents the development of a deep neural network model trained to classify OSCC using hyperspectral FTIR spectroscopy imaging. The network's performance was evaluated using accuracy, precision, recall, and F1-score metrics. The model demonstrated high effectiveness in classifying unfolded OSCC hyperspectral images, showing potential as a valuable tool for supporting diagnostic processes in clinical settings.

21 September 2025
Verified
Conference Paper
Closed access
DPDaniella L. Peres
Daniella L. Peres
DSDaniela Silva
Daniela Silva
JFJoaquim C. Felipe
Joaquim C. Felipe
LCLuciana Corrêa
Luciana Corrêa
LMLeandro Luongo Matos
Leandro Luongo Matos
Denise Maria ZezellDenise Maria Zezell
Denise Maria Zezell
This study evaluated class balancing strategies for classifying oral squamous cell carcinoma (OSCC) in FTIR hyperspectral images using the XGBoost model. Although the dataset was balanced at the image level, spectral quality filtering introduced pixel-level class imbalance. Resampling methods—SMOTE, Tomek Links, and their combination—were tested, as well as AllKNN for redundancy reduction. All approaches outperformed the unbalanced baseline, but the best overall performance metrics were achieved with the combined use of AllKNN and Tomek Links.

21 September 2025
Verified
Conference Paper
Closed access
DPDaniella L. Peres
Daniella L. Peres
DSDaniela Silva
Daniela Silva
JFJoaquim C. Felipe
Joaquim C. Felipe
LCLuciana Corrêa
Luciana Corrêa
LMLeandro Luongo Matos
Leandro Luongo Matos
Denise Maria ZezellDenise Maria Zezell
Denise Maria Zezell
This study evaluates the classification of oral squamous cell carcinoma (OSCC) using micro-FTIR hyperspectral imaging and two tree-based models: Random Forest and XGBoost. After preprocessing and PCA, class imbalance was addressed with AllKNN and Tomek Links. Both models achieved high accuracy, and key spectral bands-Amide I, II, and III-were consistently highlighted, supporting their relevance in oral cancer detection.

11 November 2024
Verified
Conference Paper
Closed access
FPFelipe Maia Prado
Felipe Maia Prado
DPDaniella Lúmara Peres
Daniella Lúmara Peres
RSRaffaele Stasi
Raffaele Stasi
Vinicius Pereira dos AnjosVinicius Pereira dos Anjos
Vinicius Pereira dos Anjos
JCJúlia Guerra Cavalero
Júlia Guerra Cavalero
Denise Maria ZezellDenise Maria Zezell
Denise Maria Zezell
This paper reviews the activities conducted by a student chapter of optics and photonics in Brazil during the 2023–2024 academic year. The initiative played a significant role within its host institution, contributing to scientific outreach and academic enrichment. The paper assesses key initiatives and their impact on both the broader community and the institution itself. We highlight several events organized during this period, which engaged over 1,500 participants. Additionally, the paper examines the benefits derived from these activities for the institutions, the participants, and the general public, emphasizing their contribution to the dissemination of optics and photonics within the community.