SAJID FAROOQ
8 resultados
Resultados de Busca
Agora exibindo 1 - 8 de 8
Artigo IPEN-doc 30192 A 3D discriminant analysis for hyperspectral FTIR images2023 - FAROOQ, SAJID; GERMANO, GLEICE; STANCARI, KLEBER A.; RAFFAELI, ROCIO; CROCE, MARIA V.; CROCE, ADELA E.; ZEZELL, DENISE M.Here, we apply a 3D discriminant analysis approach to analyze FTIR hyperspectral images of normal vs malignant Melanoma (MM) samples for skin cancer diagnosis. For this porpose we used 2 samples, for Normal (49k) and for MM(90k). Our results evidence the outstanding performance with accuracy up to 81% for big data (> 100k).Artigo IPEN-doc 30188 Identification of basal cell carcinoma skin cancer using FTIR and Machine learning2023 - PERES, DANIELLA L.; FAROOQ, SAJID; RAFFAELI, ROCIO; CROCE, MARIA V.; CROCE, ADELA E.; ZEZELL, DENISE M.Here we applied ATR-FTIR spectroscopy combined with computational modeling based on 3D-discriminant analysis (3D-PCA-QDA). Our results present an exceptional performance of 3D-discriminant algorithms to diagnose BCC skin cancer, indicating the accuracy up to 99%.Artigo IPEN-doc 30186 Monitoring changes in urine from diabetic rats using ATR-FTIR and Machine Learning2023 - FAROOQ, SAJID; PERES, DANIELLA L.; CAIXETA, DOUGLAS C.; LIMA, CASSIO; SILVA, ROBINSON S. da; ZEZELL, DENISE M.Here, we aim to better characterize diabetes mellitus (DM) by analyzing 149 urine spectral samples, comprising of diabetes versus healthy control groups employing ATR-FTIR spectroscopy, combined with a 3D discriminant analysis machine learning approach. Our results depict that the model is highly precise with accuracy close to 100%.Artigo IPEN-doc 29364 Exploring enamel demineralization from SEM images using deep learning algorithms2022 - FAROOQ, SAJID; CARAMEL-JUVINO, AMANDA; FONTES, YASMIN R.; GARDIANO, SABRINA A.; ZEZELL, DENISE M.Here, we employ segmentation and convolutional neural network (CNN) to identify and quantify enamel demineralization. Our results depict that CNN model using input SEM images achieve accuracy up to 79% for enamel demineralization diagnosis.Artigo IPEN-doc 29360 Identifying breast cancer cell lines using high performance machine learning methods2022 - FAROOQ, SAJID; DEL-VALLE, MATHEUS; SANTOS, SOFIA; BERNARDES, EMERSON S.; ZEZELL, DENISE M.We present a computational framework based on machine learning classifiers K-Nearest Neighbors and Neighborhood Component analysis for breast cancer (BC) subtypes prognostic. Our results has up to 97% accuracy for prognostic stratification of BC subtypes.Artigo IPEN-doc 29303 Superior Machine Learning Method for breast cancer cell lines identification2022 - FAROOQ, SAJID; CARAMEL-JUVINO, AMANDA; DEL-VALLE, MATHEUS; SANTOS, SOFIA; BERNARDES, EMERSON S.; ZEZELL, DENISE M.We propose an artificial intelligence platform based on machine learning (ML) algorithm using Neighborhood Component analysis and K-Nearest Neighbors for breast cancer cell lines recognition. Our model presents up to 97% accuracy for identification of breast cancer cell lines.Artigo IPEN-doc 29302 Identification of enamel demineralization using high performance convolutional neural network2022 - CARAMEL-JUVINO, AMANDA; FAROOQ, SAJID; ROMANO, MARIANA; ZEZELL, DENISE M.Here, we traces use segmentation and convolutional neural network (CNN) to trace, diagnose and quantify enamel demineralization for research. The preprocessing, histograms based methods are used to enhance the contrast and equalize the brightness through the scanning electron microscope images. Our result evidence that the deep learning based CNN model is highly efficient to process the dental image to achieve high accuracy of enamel demineralization and presents promising outcomes with optimal precision.Artigo IPEN-doc 29299 Selecting silver nanoshells for colorimetric sensors2022 - BALTAR, RAPHAEL M.S.M.; ARAUJO, RENATO E. de; FAROOQ, SAJIDIn this work the use of silver nanoshell as a starting point for the establishment of colorimetric sensor platforms, under solar illumination, was evaluated. Mie theory was explored on the analysis of the nanosensor linearity and sensitivity, considering 4 different color spaces and the influence of the nanoshell geometry. A high performance plasmonic nanoplatform was identified. The nanosensor platform based on nanoshells, with 35 nm SiO 2 core radius and 25 nm Ag shell thickness, showed sensitivity values up to 2.78 RIU -1 and linearity higher than 0.96, considering the Hue parameter of the HSV color space. The identification of optimized plasmonic nanoplatforms may extend the use naked-eye colorimetric applications in low-resource environments.