M
Muhammad Junaid Khan
Researcher at Military College of Signals
Publications - 5
Citations - 62
Muhammad Junaid Khan is an academic researcher from Military College of Signals. The author has contributed to research in topics: Deep learning & Facial recognition system. The author has an hindex of 3, co-authored 5 publications receiving 42 citations. Previous affiliations of Muhammad Junaid Khan include National University of Science and Technology.
Papers
More filters
Journal ArticleDOI
A time-varying propagation model of hot topic on BBS sites and Blog networks
TL;DR: The experimental results show that the proposed time-varying hot topic propagation model can serve as basis for predicting trends in hot online topic propagation, and reduce the computational complexity.
Journal ArticleDOI
An automated and efficient convolutional architecture for disguise-invariant face recognition using noise-based data augmentation and deep transfer learning
TL;DR: This paper has studied the efficacy of deep learning methods incorporating simple noise-based data augmentation for disguise invariant face recognition (DIFR), and compared four different pre-trained 2D CNNs based on their classification accuracy and execution time for selecting a suitable model for DIFR.
Journal ArticleDOI
A robust and efficient convolutional deep learning framework for age‐invariant face recognition
Adeel Yousaf,Muhammad Junaid Khan,Muhammad Jaleed Khan,Adil Masood Siddiqui,Khurram Khurshid +4 more
TL;DR: This work proposes a novel deep learning framework that extracts age‐invariant and generalized features from facial images of the subjects and outperforms the state‐of‐the‐art AIFR models by achieving an accuracy of 99%, which proves the effectiveness of deep learning in facial ageing research.
Proceedings ArticleDOI
Size Invariant Handwritten Character Recognition using Single Layer Feedforward Backpropagation Neural Networks
Adeel Yousaf,Muhammad Junaid Khan,Muhammad Jaleed Khan,N. Javed,Haroon Ibrahim,Khurram Khurshid,Khawar Khurshid +6 more
TL;DR: A recognition system based on neural network that follows offline handwritten characters has been proposed for Latin digits and alphabets and shows very encouraging results which are compared with the modern methods on this subject corridor.
Proceedings ArticleDOI
WLAN Location Privacy: A Client Server Based Architecture
TL;DR: The idea to obfuscate the user's location information by altering the RSSI (Received Signal Strength Identifier) value so the attacker (upon request) would receive the manipulated value and thus theuser's privacy could be preserved up to some extent is possessed.