A
Abdullah Al Hafiz Khan
Researcher at University of Maryland, Baltimore County
Publications - 25
Citations - 448
Abdullah Al Hafiz Khan is an academic researcher from University of Maryland, Baltimore County. The author has contributed to research in topics: Activity recognition & Computer science. The author has an hindex of 10, co-authored 20 publications receiving 318 citations. Previous affiliations of Abdullah Al Hafiz Khan include University of Maryland, Baltimore & Philips.
Papers
More filters
Proceedings ArticleDOI
Scaling Human Activity Recognition via Deep Learning-based Domain Adaptation
TL;DR: A transductive transfer learning model that is specifically tuned to the properties of convolutional neural networks (CNNs) is proposed, called HDCNN, which assumes that the relative distribution of weights in the different CNN layers will remain invariant, as long as the set of activities being monitored does not change.
Proceedings ArticleDOI
Active learning enabled activity recognition
TL;DR: This paper investigates and analyze different active learning strategies to scale activity recognition and proposes a dynamic k-means clustering based active learning approach and results on real data traces from a retirement community help validate the early promise of this approach.
Proceedings ArticleDOI
TransAct: Transfer learning enabled activity recognition
TL;DR: This work augments the Instance based Transfer Boost algorithm with k-means clustering and demonstrates that the TransAct model outperforms traditional activity recognition approaches.
Proceedings ArticleDOI
Acoustic based appliance state identifications for fine-grained energy analytics
TL;DR: This work correlates an appliance's inherent acoustic noise with its energy consumption pattern individually and in presence of multiple appliances and proposes a probabilistic graphical model, based on a variation of Factorial Hidden Markov Model for multiple appliances energy disaggregation, which is combined with the appliances acoustic analytics and postulate a hybrid model for energy disag segregation.
Proceedings ArticleDOI
RAM: Radar-based activity monitor
Abdullah Al Hafiz Khan,Ruthvik Kukkapalli,Piyush Waradpande,Sekar Kulandaivel,Nilanjan Banerjee,Nirmalya Roy,Ryan Robucci +6 more
TL;DR: A low-cost heterogeneous Radar based Activity Monitoring (RAM) system for recognizing fine-grained activities by exploiting the feasibility of using an array of heterogeneous micro-doppler radars to recognize low-level activities.