Search

Your search keyword '"Nasir, Nida"' showing total 78 results
Start Over Author "Nasir, Nida"
78 results on '"Nasir, Nida"'

2. Deep Learning Classification of Photoplethysmogram Signal for Hypertension Levels

Author

Nasir, Nida, Sameer, Mustafa, Barneih, Feras, Alshaltone, Omar, and Ahmed, Muneeb

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia
Abstract

Continuous photoplethysmography (PPG)-based blood pressure monitoring is necessary for healthcare and fitness applications. In Artificial Intelligence (AI), signal classification levels with the machine and deep learning arrangements need to be explored further. Techniques based on time-frequency spectra, such as Short-time Fourier Transform (STFT), have been used to address the challenges of motion artifact correction. Therefore, the proposed study works with PPG signals of more than 200 patients (650+ signal samples) with hypertension, using STFT with various Neural Networks (Convolution Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), followed by machine learning classifiers, such as, Support Vector Machine (SVM) and Random Forest (RF). The classification has been done for two categories: Prehypertension (normal levels) and Hypertension (includes Stage I and Stage II). Various performance metrics have been obtained with two batch sizes of 3 and 16 for the fusion of the neural networks. With precision and specificity of 100% and recall of 82.1%, the LSTM model provides the best results among all combinations of Neural Networks. However, the maximum accuracy of 71.9% is achieved by the LSTM-CNN model. Further stacked Ensemble method has been used to achieve 100% accuracy for Meta-LSTM-RF, Meta- LSTM-CNN-RF and Meta- STFT-CNN-SVM.

Published
2024

3. Alzheimer's Magnetic Resonance Imaging Classification Using Deep and Meta-Learning Models

Author

Nasir, Nida, Ahmed, Muneeb, Afreen, Neda, and Sameer, Mustafa

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Emerging Technologies, Computer Science - Machine Learning, Computer Science - Multimedia
Abstract

Deep learning, a cutting-edge machine learning approach, outperforms traditional machine learning in identifying intricate structures in complex high-dimensional data, particularly in the domain of healthcare. This study focuses on classifying Magnetic Resonance Imaging (MRI) data for Alzheimer's disease (AD) by leveraging deep learning techniques characterized by state-of-the-art CNNs. Brain imaging techniques such as MRI have enabled the measurement of pathophysiological brain changes related to Alzheimer's disease. Alzheimer's disease is the leading cause of dementia in the elderly, and it is an irreversible brain illness that causes gradual cognitive function disorder. In this paper, we train some benchmark deep models individually for the approach of the solution and later use an ensembling approach to combine the effect of multiple CNNs towards the observation of higher recall and accuracy. Here, the model's effectiveness is evaluated using various methods, including stacking, majority voting, and the combination of models with high recall values. The majority voting performs better than the alternative modelling approach as the majority voting approach typically reduces the variance in the predictions. We report a test accuracy of 90% with a precision score of 0.90 and a recall score of 0.89 in our proposed approach. In future, this study can be extended to incorporate other types of medical data, including signals, images, and other data. The same or alternative datasets can be used with additional classifiers, neural networks, and AI techniques to enhance Alzheimer's detection.

Published
2024

18. Challenges of Artificial Intelligence in Medicine

Author

Nasir, Nida, primary, Alshabi, Mohammad, additional, Al-Yateem, Nabeel, additional, Rahman, Syed Azizur, additional, Subu, Muhammad Arsyad, additional, Hijazi, Heba Hesham, additional, Ahmed, Fatma Refaat, additional, Dias, Jacqueline Maria, additional, Al Marzouqi, Amina, additional, Alkhawaldeh, Mohammad Yousef, additional, Eid AbuRuz, Mohannad, additional, and Saifan, Ahmad Rajeh, additional

Published
2023
Full Text
View/download PDF

19. Review of Machine Learning Advancements for Single-Cell Analysis

Author

Nasir, Nida, primary, Alshabi, Mohammad, additional, Al-Yateem, Nabeel, additional, Rahman, Syed Azizur, additional, Arsyad Subu, Muhammad, additional, Hijazi, Heba Hesham, additional, Refaat Ahmed, Fatma, additional, Dias, Jacqueline Maria, additional, Al Marzouqi, Amina, additional, Alkhawaldeh, Mohammad Yousef, additional, Rajeh Saifan, Ahmad, additional, and AbuRuz, Mohannad Eid, additional

Published
2023
Full Text
View/download PDF

41. Cells Electrical Characterization: Dielectric Properties, Mixture, and Modeling Theories

Author

Nasir, Nida and Al Ahmad, Mahmoud

Subjects
Article Subject
Abstract

Electrical detection of biotic materials and their properties is always crucial in Biomedical Engineering. It emphasizes elaborate analysis of a certain disease diagnosis using electrical means which includes the study of electrical properties followed by detection, identification, and quantification of biotic entities. Proper and early detection of cells, which can be normal or cancerous, holds never-ending demand. This review emphasizes the electrical characterization methods in modeling and classification of cell properties. Moreover, standard methods have been highlighted and discussed to yield performance analysis. This study suggests that techniques presented for single-cell analysis (SCA) are always precise and hold great scope compared to those for cell mixture. SCA plays a promising role in disease diagnosis and treatment planning, as it not only detects the cells but also helps in identification. Distinct electrical-based cell detection techniques are highlighted, along with the pros and cons of various SCA devices. The content, in terms of methodologies and available techniques, of this review paper is useful to attract researchers working in this area.

Published
2020
Full Text
View/download PDF

42. Electrical Characterization and Detection of Blood Cells and Stones in Urine

Author

Dr. Mahmoud F. AI Ahmad, Dr. Ahmed H. Al-Marzouqi, Dr. Mohammad Shakeel Laghari, Nasir, Nida, Dr. Mahmoud F. AI Ahmad, Dr. Ahmed H. Al-Marzouqi, Dr. Mohammad Shakeel Laghari, and Nasir, Nida

Abstract

Urine contains an immense amount of information related to its physical, chemical, and biological components; hence, it is a promising tool in detecting various diseases. Available methods for detecting hematuria (blood in the urine) are not accurate. Results are influenced by many factors, such as, health and vitals of the patients, settings of the equipment and laboratories, which leads to false positive or false negative outputs. This necessitates the development of new, accurate, and easy-access methods that save time and effort. This study demonstrates a label-free and accurate method for detecting the presence of red and white blood cells (RBCs and WBCs) in urine by measuring the changes in the dielectric properties of urine upon increasing concentrations of both cell types. The current method could detect changes in the electrical properties of fresh urine over a short time interval, making this method suitable for detecting changes that cannot be recognized by conventional methods. Correcting these changes enabled the detection of a minimum cell concentration of 10² RBCs per ml which is not possible by conventional methods used in the labs except for the semi-quantitative method that can detect 50 RBCs per ml, but it is a lengthy and involved procedure, not suitable for high volume labs. This ability to detect a very small amount of both types of cells makes the proposed technique an attractive tool for detecting hematuria, the presence of which is indicative of problems in the excretory system. Furthermore, urolithiasis is also a very common problem worldwide, affecting adults, kids, and even animals. Calcium oxalate is the major constituent of urinary tract stones in individuals, primarily due to the consumption of high oxalate foods. The occurrence of urinary oxalate occurs by endogenous synthesis, especially in the upper urinary tract. In a normal, healthy individual, the excretion of oxalate ranges from 10 to 45 mg/day, depending on the age an

Published
2020

45. Adsorptive removal of methyl orange from wastewaters by the commercial anion exchange membrane EPTAC.

Author

Khana, Muhammad Imran, Shanableh, Abdallah, Nasir, Nida, and Shahida, Shabnam

Subjects
INDUSTRIAL wastes, ADSORPTION kinetics, ANIONS, IONIC strength, AQUEOUS solutions, COLOR removal (Sewage purification), SORBENTS
Abstract

In this manuscript, we have utilized the commercially available anion exchange membrane EPTAC for the adsorptive removal of methyl orange (MO) dye from wastewater via batch mode at room temperature. The percentage removal of MO was increased from 26.10% to 98.70% with the contact time, and from 48.04% to 98.70% with the amount of adsorbent (membrane dosage). On the other hand, the percentage removal of MO was decreased with an initial concentration of dye aqueous solution, temperature and ionic strength. Adsorption kinetics evaluation showed that experimental data for adsorption of MO onto the commercial anion exchange membrane EPTAC fitted-well to pseudo-second-order model because the value of correlation coefficient (R2) was very close to unit (R2 > 0.995). Several nonlinear isotherms containing two parameters and three parameters isotherms were applied on experimental data of MO adsorption onto the commercial anion exchange membrane EPTAC. Results demonstrated that adsorption MO onto the commercial anion exchange membrane EPTAC fitted well to nonlinear Freundlich isotherm with the lower value of chi-square (2 = 2.22 × 10-9) Moreover, adsorption thermodynamics of MO adsorption onto the commercial anion exchange membrane EPTAC was also evaluated in detail. The negative value of enthalpy of the system (H° = -68.93 kJ/mol) showed that adsorption of MO onto the commercial anion exchange membrane EPTAC was an exothermic process. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results