Junaid Ali Khan,

Dr. Junaid Ali Khan,


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 March 2017 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
FCF. A. Chaudhry
F. A. Chaudhry
MAM. Amin
M. Amin
MIM. Iqbal
M. Iqbal
RKR. D. Khan
R. D. Khan
JKJunaid Ali Khan,
Junaid Ali Khan,

17 October 2022 in Buildings
Verified
Journal Article
Open access
PDF file
MBMubeen ul Basharat
Mubeen ul Basharat
JKJunaid Ali Khan,
Junaid Ali Khan,
UKumer khalil
umer khalil
Aqil TariqAqil Tariq
Aqil Tariq
BABilal Aslam
Bilal Aslam
QLQingting Li
Qingting Li
Northern Pakistan, the center of major construction projects due to the commencement of the China Pakistan Economic Corridor, is among the most earthquake-prone regions globally owing to its tectonic settings. The area has experienced several devastating earthquakes in the past, and these earthquakes pose a severe threat to infrastructure and life. Several researchers have previously utilized advanced tools such as Machine Learning (ML) and Deep Learning (DL) algorithms for earthquake predictions. This technological advancement helps with construction innovation, for instance, by designing earthquake-proof buildings. However, previous studies have focused mainly on temporal rather than spatial variables. The present study examines the impact of spatial variables to assess the performance of the different ML and DL algorithms for predicting the magnitude of short-term future earthquakes in North Pakistan. Two ML methods, namely Modular Neural Network (MNN) and Shallow Neural Network (SNN), and two DL methods, namely Recurrent Neural Network (RNN) and Deep Neural Network (DNN) algorithms, were used to meet the research objectives. The performance of the techniques was assessed using statistical measures, including accuracy, information gain analysis, sensitivity, specificity, and positive and negative predictive values. These metrics were used to evaluate the impact of including a new variable, Fault Density (FD), and the standard seismic variables in the predictions. The performance of the proposed models was examined for different patterns of variables and different classes of earthquakes. The accuracy of the models for the training data ranged from 73% to 89%, and the accuracy for the testing data ranged from 64% to 85%. The analysis outcomes demonstrated an improved performance when using an additional variable of FD for the earthquakes of low and high magnitudes, whereas the performance was less for moderate-magnitude earthquakes. DNN, and SNN models, performed relatively better than other models. The results provide valuable insights about the influence of the spatial variable. The outcome of the present study adds to the existing pool of knowledge about earthquake prediction, fostering a safer and more secure regional development plan involving innovative construction.

21 April 2021 in Electronics
Verified
Journal Article
Open access
PDF file
JTjunaid tariq
junaid tariq
Ammar ArmghanAmmar Armghan
Ammar Armghan
FAFayadh Alenezi
Fayadh Alenezi
AIAmir Ijaz
Amir Ijaz
SRSaad Rehman
Saad Rehman
JKJunaid Ali Khan,
Junaid Ali Khan,
High-Efficiency Video Coding (HEVC) applies 35 intra modes to every block of a frame and selects the mode that gives the best prediction. This brute-force nature of HEVC makes it complex and unfit for real-time applications. Therefore, a fast intra-mode estimation algorithm is presented here based on the classic World War II (WW2) technique known as the ‘German Tanks Problem’ (GTP). This not only is the first article to use GTP for early estimation of intra mode, but also expedites the estimation process of GTP. Secondly, the various elements of the intra process are efficiently mapped to the elements of GTP estimation. Finally, the two variations of GPT are modeled and are also minimum-variance estimates. These experimental results indicate that proposed GTP-based fast estimation reduced the compression time of HEVC from 23.88% to 31.44%.

29 September 2025 in Soft Computing
Verified
Journal Article
Closed access
PDF file
FRFarhad Muhammad Riaz
Farhad Muhammad Riaz
RURaja Muhammad Shamayel Ullah
Raja Muhammad Shamayel Ullah
AAAreej Alasiry
Areej Alasiry
MMMehrez Marzougui
Mehrez Marzougui
JKJunaid Ali Khan,
Junaid Ali Khan,

28 April 2025 in Research Square
Verified
Preprint
Open access
PDF file
FRFarhad Muhammad Riaz
Farhad Muhammad Riaz
JKJunaid Ali Khan,
Junaid Ali Khan,
WBWided Bouchelligua
Wided Bouchelligua
HAHend Alshaya
Hend Alshaya
Controlling epidemiology with stochastic intelligence systems, particularly those based on feed-forward artificial neural networks (ANNs), has advanced significantly in recent years. These techniques provide an effective framework for studying the dynamics of epidemic diseases while also addressing the intricacy and nonlinearity of the linked epidemic model based on the differential system. With the computational efficiency of a single-layer feed-forward artificial neural network, the current study designs a swarming-optimized neuro-heuristic technique to solve the nonlinear system based on Leptospirosis disease (LD). The proposed strategies utilize the computational efficiency of Mexican Hat Wavelet (MHW) modeling, i.e. (MHW-ANNs-PSO-SQP), in addition to the optimization process of global search Particle Swarm Optimisation (PSO), which is aided by the efficient local search Sequential Quadratic Programming (SQP). A zoonotic disease called LD spreads from animals to humans and kills them. The mathematical model of LD is based on the conventional susceptible-infected-recovered (SIR) model, which is used to solve the dynamics of the disease's spread. The differential coupled system has been used to solve the LD nonlinear epidemic model by developing an unsupervised error-based merit function. To confirm the accuracy, the outcomes are contrasted with the well-known Runge-Kutta (RK) numerical and genetic algorithms hybrid with active set algorithms, such as the GA-ASA-based ANN solver. Additionally, the correctness and reliability of the MHW-ANNs-PSO-SQP are verified using absolute error and comprehensive statistical analysis employing many statistical operators. Furthermore, the complexity of the suggested approach is examined using the Mean Execution Time. The AE values for mean and best cases are in the range 10− 11 to 10− 14 and 10− 14 to 10− 15 respectively, while the MSE, MAD, and TIC values are in the range 10− 7 to 10− 11, 10− 7 to 10− 11 and 10− 6 to 10− 10 respectively. The results demonstrate that the developed scheme solves the LD model accurately and precisely. The developed scheme is consistent, stable, and reliable.