A
Abdulmajid Murad
Researcher at Norwegian University of Science and Technology
Publications - 8
Citations - 361
Abdulmajid Murad is an academic researcher from Norwegian University of Science and Technology. The author has contributed to research in topics: Reinforcement learning & Deep learning. The author has an hindex of 3, co-authored 7 publications receiving 235 citations. Previous affiliations of Abdulmajid Murad include Chosun University.
Papers
More filters
Journal ArticleDOI
Deep Recurrent Neural Networks for Human Activity Recognition.
Abdulmajid Murad,Jae-Young Pyun +1 more
TL;DR: Experimental results show that the proposed deep recurrent neural networks (DRNNs) used for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs.
Proceedings ArticleDOI
Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning
TL;DR: In this paper, the authors use policy-gradient approaches to learn capable policies, leading to behavior more appropriate for IoT nodes with less manual design effort, increasing the level of autonomy in IoT.
Proceedings ArticleDOI
Information-driven adaptive sensing based on deep reinforcement learning
TL;DR: A novel reward function based on the Fisher information value is presented and studied, which enables IoT sensor devices to learn to spend available energy on measurements at otherwise unpredictable moments, while conserving energy at times when measurements would provide little new information.
Proceedings ArticleDOI
IoT Sensor Gym: Training Autonomous IoT Devices with Deep Reinforcement Learning
TL;DR: IoT Sensor Gym is described, a framework to train the behavior of constrained IoT devices using deep reinforcement learning and exemplify the results with the autonomous control of a solar-powered IoT device.
Proceedings ArticleDOI
Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning
TL;DR: It is shown that a reward function and policy-gradient approaches to RL are appropriate for the IoT domain and that they outperform previous approaches, leading to behavior more appropriate for IoT nodes with less manual design effort, increasing the level of autonomy in IoT.