no code implementations • 14 May 2024 • Muhammad Usama, Yunkyung Hwang, Jaehong Kim
This paper proposed a straightforward and efficient current control solution for induction machines employing deep symbolic regression (DSR).
no code implementations • 13 Feb 2024 • Muhammad Usama, Zahid Masood, Shahroz Khan, Konstantinos Kostas, Panagiotis Kaklis
In this work, we perform a systematic comparison of the effectiveness and efficiency of generative and non-generative models in constructing design spaces for novel and efficient design exploration and shape optimization.
no code implementations • 12 Sep 2023 • Syed Waleed Hyder, Muhammad Usama, Anas Zafar, Muhammad Naufil, Fawad Javed Fateh, Andrey Konin, M. Zeeshan Zia, Quoc-Huy Tran
This paper presents a 2D skeleton-based action segmentation method with applications in fine-grained human activity recognition.
1 code implementation • 10 May 2022 • Archit Parnami, Muhammad Usama, Liyue Fan, Minwoo Lee
Requiring less data for accurate models, few-shot learning has shown robustness and generality in many application domains.
3 code implementations • 11 Feb 2022 • Muhammad Usama, Hafeez Anwar, Abbas Anwar, Saeed Anwar
The best Mean Average Precision (mAP@0. 5) of 98. 8% for vehicle type recognition, 98. 5% for license plate detection, and 98. 3% for license plate reading is achieved by YOLOv4, while its lighter version, i. e., Tiny YOLOv4 obtained a mAP of 97. 1%, 97. 4%, and 93. 7% on vehicle type recognition, license plate detection, and license plate reading, respectively.
no code implementations • 3 Jan 2021 • Bilal Yousaf, Muhammad Usama, Waqas Sultani, Arif Mahmood, Junaid Qadir
The proposed detector has demonstrated significant performance improvement compared to the current state-of-the-art fake content detectors and fusing the frequency and spatial domain streams has also improved generalization of the detector.
no code implementations • 22 Dec 2020 • Inaam Ilahi, Muhammad Usama, Muhammad Omer Farooq, Muhammad Umar Janjua, Junaid Qadir
The anticipated increase in the count of IoT devices in the coming years motivates the development of efficient algorithms that can help in their effective management while keeping the power consumption low.
no code implementations • 5 Sep 2020 • Muhammad Usama, Rupendra Nath Mitra, Inaam Ilahi, Junaid Qadir, Mahesh K. Marina
Spurred by the recent advances in deep learning to harness rich information hidden in large volumes of data and to tackle problems that are hard to model/solve (e. g., resource allocation problems), there is currently tremendous excitement in the mobile networks domain around the transformative potential of data-driven AI/ML based network automation, control and analytics for 5G and beyond.
1 code implementation • 27 Jan 2020 • Inaam Ilahi, Muhammad Usama, Junaid Qadir, Muhammad Umar Janjua, Ala Al-Fuqaha, Dinh Thai Hoang, Dusit Niyato
Deep Reinforcement Learning (DRL) has numerous applications in the real world thanks to its outstanding ability in quickly adapting to the surrounding environments.
no code implementations • 1 Aug 2019 • Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha
We have evaluated the robustness of two famous such modulation classifiers (based on the techniques of convolutional neural networks and long short term memory) against adversarial machine learning attacks in black-box settings.
1 code implementation • 17 Jun 2019 • Muhammad Usama, Dong Eui Chang
We introduce entropy-based exploration (EBE) that enables an agent to explore efficiently the unexplored regions of state space.
no code implementations • 3 Jun 2019 • Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha, Mounir Hamdi
We also provide some guidelines to design secure ML models for cognitive networks that are robust to adversarial attacks on the ML pipeline of cognitive networks.
no code implementations • 29 May 2019 • Adnan Qayyum, Muhammad Usama, Junaid Qadir, Ala Al-Fuqaha
Connected and autonomous vehicles (CAVs) will form the backbone of future next-generation intelligent transportation systems (ITS) providing travel comfort, road safety, along with a number of value-added services.
no code implementations • 22 Nov 2018 • Muhammad Usama, Dong Eui Chang
Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and better architectures.
no code implementations • 19 Sep 2017 • Muhammad Usama, Junaid Qadir, Aunn Raza, Hunain Arif, Kok-Lim Alvin Yau, Yehia Elkhatib, Amir Hussain, Ala Al-Fuqaha
We provide a comprehensive survey highlighting the recent advancements in unsupervised learning techniques and describe their applications for various learning tasks in the context of networking.