activity
20182022
most citedHAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data

12 citations · 12 across the 1 of their papers we have counts for

collaborators

6 papers

cs.CV202212 cited

HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data

Abduallah Mohamed, Fernando Lejarza, Stephanie Cahail +2

The problem of human activity recognition from mobile sensor data applies to multiple domains, such as health monitoring, personal fitness, daily life logging, and senior care. A c…

cs.LG2020

Inner Ensemble Networks: Average Ensemble as an Effective Regularizer

Abduallah Mohamed, Muhammed Mohaimin Sadiq, Ehab AlBadawy +2

We introduce Inner Ensemble Networks (IENs) which reduce the variance within the neural network itself without an increase in the model complexity. IENs utilize ensemble parameters…

cs.CV2020

Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction

Abduallah Mohamed, Kun Qian, Mohamed Elhoseiny +1

Better machine understanding of pedestrian behaviors enables faster progress in modeling interactions between agents such as autonomous vehicles and humans. Pedestrian trajectories…

eess.SP2019

Physics Informed Data Driven model for Flood Prediction: Application of Deep Learning in prediction of urban flood development

Kun Qian, Abduallah Mohamed, Christian Claudel

Flash floods in urban areas occur with increasing frequency. Detecting these floods would greatlyhelp alleviate human and economic losses. However, current flood prediction methods…

cs.LG2018

IEA: Inner Ensemble Average within a convolutional neural network

Abduallah Mohamed, Xinrui Hua, Xianda Zhou +1

Ensemble learning is a method of combining multiple trained models to improve model accuracy. We propose the usage of such methods, specifically ensemble average, inside Convolutio…

cs.NE2018

MCRM: Mother Compact Recurrent Memory

Abduallah A. Mohamed, Christian Claudel

LSTMs and GRUs are the most common recurrent neural network architectures used to solve temporal sequence problems. The two architectures have differing data flows dealing with a c…