CORTEXA
← Browse

Jawad F. Al‐Asad

4 papers indexed

openalexSensors2023-07-24Cited by 14

Gaussian-Filtered High-Frequency-Feature Trained Optimized BiLSTM Network for Spoofed-Speech Classification

Hiren Mewada, Jawad F. Al‐Asad, Faris A. Almalki, Adil H. Khan, Nouf Abdullah Almujally, Samir El-Nakla, et al.

Voice-controlled devices are in demand due to their hands-free controls. However, using voice-controlled devices in sensitive scenarios like smartphone applications and financial transactions requires protection against fraudulent attacks referred to as "speech spoofing". The alg…

Also available via: Multidisciplinary Digital Publishing Institute

View free PDFSource page
openalexThe Open Biomedical Engineering Journal2021-12-31Cited by 5

Multi-Channel Local Binary Pattern Guided Convolutional Neural Network for Breast Cancer Classification

Hiren Mewada, Jawad F. Al‐Asad, Amit Patel, Jitendra Chaudhari, Keyur Mahant, Alpesh Vala

Background: The advancement in convolutional neural network (CNN) has reduced the burden of experts using the computer-aided diagnosis of human breast cancer. However, most CNN networks use spatial features only. The inherent texture structure present in histopathological images…

Also available via: Bentham Science Publishers

View free PDFSource page
openalexJournal of Electrical Engineering2021-08-01Cited by 4

Frequency domain despeckling technique for medical ultrasound images

Jawad F. Al‐Asad, Hiren Mewada, Adil H. Khan, Nidal Abu-Libdeh, Jamal Nayfeh

Abstract This work proposes a novel frequency domain despeckling technique pertaining to the enhancement of the quality of medical ultrasound images. The results of the proposed method have been validated in comparison to both the time-domain and the frequency-domain projections…

Also available via: De Gruyter

View free PDFSource page
openalexPeerJ Computer Science2021-05-27Cited by 3

A fast region-based active contour for non-rigid object tracking and its shape retrieval

Hiren Mewada, Jawad F. Al‐Asad, Amit Patel, Jitendra Chaudhari, Keyur Mahant, Alpesh Vala

Conventional tracking approaches track objects using a rectangle bounding box. Gait, gesture and many medical analyses require non-rigid shape extraction. A non-rigid object tracking is more difficult because it needs more accurate object shape and background separation in contra…

Also available via: PeerJ, Inc.

View free PDFSource page