M
Muhammad Alrabeiah
Researcher at Arizona State University
Publications - 40
Citations - 1925
Muhammad Alrabeiah is an academic researcher from Arizona State University. The author has contributed to research in topics: Wireless & Overhead (computing). The author has an hindex of 14, co-authored 36 publications receiving 1026 citations. Previous affiliations of Muhammad Alrabeiah include King Saud University & McMaster University.
Papers
More filters
Posted Content
Deep Learning for Moving Blockage Prediction using Real Millimeter Wave Measurements.
TL;DR: In this paper, a machine learning algorithm is proposed to predict future blockages by observing what is referred to as the pre-blockage signature, which can be used to enhance the reliability and latency of future wireless networks.
Journal ArticleDOI
Progressive With Purpose: Guiding Progressive Inpainting DNNs Through Context and Structure
Kangdi Shi,Muhammad Alrabeiah,Jun Chen Department of Electrical,Computer Engineering,McMaster University,Hamilton,Canada,Electrical Engineering Department,King Saud University,Saudi Arabia +9 more
TL;DR: A novel progressive inpainting network that maintains the structural and contextual integrity of a processed image in an iterative manner is proposed and achieves clear improvement in performance over many state-of-the-art inPainting algorithms.
Posted Content
Vision-Aided 6G Wireless Communications: Blockage Prediction and Proactive Handoff
TL;DR: In this paper, a deep learning algorithm is proposed to predict incoming blockages and initiate user hand-off in wireless networks, which can be used by the wireless network to proactively initiate handoff decisions and avoid any unnecessary latency.
Patent
Persistent feature descriptors for video
TL;DR: In this article, a method for extracting feature descriptors for a video, the video having a sequence of pictures, is presented, where the method includes identifying a first key picture and a second key picture later in the sequence than the first key pictures; extracting a first set of descriptors from the first and second key pictures, where each pair includes one descriptor from the one set and one descriptor from the second set; generating motion information describing the motion field between the first Key Picture and the second Key Picture; and filtering the set of pairs of feature descriptor based on correlation with
Proceedings ArticleDOI
Image Retrieval via Canonical Correlation Analysis
TL;DR: The proposed CCA approach is shown to achieve competitive retrieval performances on popular datasets such as Oxford5k and Paris6k and is bench-marked against two popular statistical analysis methods, Linear Discriminant Analysis (LDA) and Principal Component Analysis with whitening (PCAw).