A Fast and Robust Gas Recognition Algorithm Based on Hybrid Convolutional and Recurrent Neural Network by Xiaofang Pan (1895950)

STEM: spatial speech separation using twin-delayed DDPG reinforcement learning and expectation maximization by Muhammad Salman Khan (7202543)

“…In this paper, a novel speech separation algorithm is proposed that integrates the twin-delayed deep deterministic (TD3) policy gradient reinforcement learning (RL) agent with the expectation maximization (EM) algorithm for clustering the spatial cues of individual sources separated on azimuth. …”

On the Optimization of Band Gaps in Periodic Waveguides by Jamil Renno (14070771)

Subjects:

CNN and HEVC Video Coding Features for Static Video Summarization by Issa, Obada

Get full text

Novel algorithms for accurate DNA base-calling by Mohammed, Omniyah Gul

Get full text

Predicting Patient ICU Readmission Using Recurrent Neural Networks With Long Short-Term Memory by Nadia Rasheed (22997257)

Leveraging Machine and Deep Learning Algorithms for hERG Blocker Prediction by Syed Mohammad (21075689)

“…The application of machine learning (ML) and deep learning (DL) models in the field of toxicity has gained burgeoning interest. …”

A combined algorithm based on finite elements and a modified methodof characteristics for the analysis of the corona in wire-ductelectrostatic precipitators by Al-Hamouz, Z.M.

Get full text
Get full text

A reduced model for phase-change problems with radiation using simplified PN approximations by Belhamadia, Youssef

“…The integro-differential equation for the full radiative transfer is replaced by a set of differential equations which are independent of the angle variable and easy to solve using conventional computational methods. To solve the coupled equations, we implement a second-order implicit scheme for the time integration and a mixed finite element method for the space discretization. …”
Get full text

Extended Behavioral Modeling of FET and Lattice-Mismatched HEMT Devices by Khawam, Yahya Bader

Subjects: Get full text

Brain Source Localization in the Presence of Leadfield Perturbations by Momin, Rabiya Nakhat

Get full text

Enhancing Breast Cancer Diagnosis With Bidirectional Recurrent Neural Networks: A Novel Approach for Histopathological Image Multi-Classification by Rajendra Babu Chikkala (22330876)

“…<p dir="ltr">In recent years, deep learning methods have dramatically improved medical image analysis, though earlier models faced difficulties in capturing intricate spatial and contextual details. …”

Monitoring Bone Density Using Microwave Tomography of Human Legs: A Numerical Feasibility Study by Alkhodari, Mohanad Ahmed

“…This study was performed using an in-house finite-element method contrast source inversion algorithm (FEM-CSI). …”
Get full text

Deep Learning-Based Coding Strategy for Improved Cochlear Implant Speech Perception in Noisy Environments by Billel Essaid (22047578)

The Use of Microwave Tomography in Bone Healing Monitoring by Alkhodari, Mohanad Ahmed

Get full text

IntruSafe: a FCNN-LSTM hybrid IoMT intrusion detection system for both string and 2D-spatial data using sandwich architecture by Moutaz Alazab (17730060)

Design of acoustic absorbing metasurfaces using a data-driven approach by Hamza Baali (14603380)

Subjects:

Design of adaptive arrays based on element position perturbations by Dawoud, M.M.

“…The main advantage of using this technique over the other commonly used methods is that the amplitudes and phases of the array elements can be used mainly to steer the main beam towards the desired signal. …”
Get full text
Get full text

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network by Sakib Mahmud (15302404)

“…Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. …”

Nonlinear analysis of shell structures using image processing and machine learning by M.S. Nashed (16392961)

“…The proposed approach can be significantly more efficient than training a machine learning algorithm using the raw numerical data. To evaluate the proposed method, two different structures are assessed where the training data is created using nonlinear finite element analysis. …”