Muhammad Saqib is a Postdoctoral Research Fellow, at the School of Computer Science, Faculty of Engineering & IT at UTS. He completed PhD studies at the School of Computer Science. His research interests are in:
- Pedestrian crowd anaysis using computer vision and machine learning
- Object detection and recognition
- Image and video processing
- Data Analytics
- Deep Learning and Convolutional Neural Network Autumn 2019
- Introduction to Data Analytics 2019
- Application development in .NET
- Crowd analysis, Motion flow analysis, Crowd behavior understanding
- Object detection and recognition
- Deep Convolutional Neural Networks
- Visual C#.NET
- Data Analytics
- Computer Vision
- Image and Video Processing
- Python Programming
Saqib, M, Khan, SD, Sharma, N & Blumenstein, M 2019, 'Crowd Counting in Low-Resolution Crowded Scenes Using Region-Based Deep Convolutional Neural Networks', IEEE Access, vol. 7, pp. 35317-35329.View/Download from: UTS OPUS or Publisher's site
© 2013 IEEE. Crowd counting and density estimation is an important and challenging problem in the visual analysis of the crowd. Most of the existing approaches use regression on density maps for the crowd count from a single image. However, these methods cannot localize individual pedestrian and therefore cannot estimate the actual distribution of pedestrians in the environment. On the other hand, detection-based methods detect and localize pedestrians in the scene, but the performance of these methods degrades when applied in high-density situations. To overcome the limitations of pedestrian detectors, we proposed a motion-guided filter (MGF) that exploits spatial and temporal information between consecutive frames of the video to recover missed detections. Our framework is based on the deep convolution neural network (DCNN) for crowd counting in the low-to-medium density videos. We employ various state-of-the-art network architectures, namely, Visual Geometry Group (VGG16), Zeiler and Fergus (ZF), and VGGM in the framework of a region-based DCNN for detecting pedestrians. After pedestrian detection, the proposed motion guided filter is employed. We evaluate the performance of our approach on three publicly available datasets. The experimental results demonstrate the effectiveness of our approach, which significantly improves the performance of the state-of-the-art detectors.
Nawaz, M, Saqib, MA, Kashif, SAR & Gul, M 2019, 'Constrained model predictive control for an induction heating load', Transactions of the Institute of Measurement and Control, vol. 41, no. 1, pp. 210-218.View/Download from: UTS OPUS or Publisher's site
© The Author(s) 2018. This paper explores a model predictive control (MPC) strategy with constraints satisfaction for a high power induction heating load. The MPC predicts the state variables and future control sequence of the system in advance and achieves on-line-optimization with a reduced error. The state-space model of the system with a parallel resonant load is developed and then MPC is applied. The proposed approach controls the DC link current at the rectifier output and reactive component of the supply current. The DC current is used to regulate the power of the heating load and the reactive component of input current is kept at zero to attain the unity power factor. The results show that the proposed strategy regulates the power of the heating load, achieves unity power factor at input of the system and handles the variables within the defined constraints effectively.
Saqib, M, Ali, F, Khan, I, Sheikh, NA & Shafie, SB 2019, 'Convection in ethylene glycol-based molybdenum disulfide nanofluid: Atangana–Baleanu fractional derivative approach', Journal of Thermal Analysis and Calorimetry, vol. 135, no. 1, pp. 523-532.View/Download from: UTS OPUS or Publisher's site
© 2018, Akadémiai Kiadó, Budapest, Hungary. This article aims to study the flow of ethylene glycol-based molybdenum disulfide generalized nanofluid over an isothermal vertical plate. A fractional model with non-singular and non-local kernel, namely Atangana–Baleanu fractional derivatives, is developed for Casson nanofluid in the form of partial differential equations along with appropriate initial and boundary conditions. Molybdenum disulfide nanoparticles of spherical shape are suspended in ethylene glycol taken as conventional base fluid. The exact solutions are developed for velocity and temperature via the Laplace transform technique. In limiting sense, the obtained solutions are reduced to fractional Newtonian (β→ ∞) , classical Casson fluid (α→ 1) and classical Newtonian nanofluid. The influence of various pertinent parameters is analyzed in various plots with the useful physical discussion.
Ali, F, Arif, M, Khan, I, Sheikh, NA & Saqib, M 2018, 'Natural convection in polyethylene glycol based molybdenum disulfide nanofluid with thermal radiation, chemical reaction and ramped wall temperature', International Journal of Heat and Technology, vol. 36, no. 2, pp. 619-631.View/Download from: UTS OPUS or Publisher's site
© 2018 International Information and Engineering Technology Association. All Rights Reserved. The aim of this study is to investigate the unsteady magnetohydrodynamic (MHD) flow of Casson nanofluid over an infinite oscillating vertical plate with ramped wall temperature. The effects of porosity, thermal radiation and first order chemical reaction have been considered. Polyethylene glycol (PEG) is chosen as base fluid which contained molybdenum disulfide (MoS2 ) nanoparticles. The Laplace transform technique is applied to the momentum, energy and concentration equations to obtain the closed form solutions. The obtained solutions are for both cases ramped and isothermal boundary conditions and compared graphically. From graphical analysis, it is observed that for isothermal plate, the magnitude of velocity, temperature and concentration profiles are greater than ramped wall temperature. Skin-friction, Nusselt number and Sherwood number are evaluated and presented in tabular forms. The effects of various embedded parameters on velocity, temperature and concentration profiles are discussed graphically.
Jan, SAA, Ali, F, Sheikh, NA, Khan, I, Saqib, M & Gohar, M 2018, 'Engine oil based generalized brinkman-type nano-liquid with molybdenum disulphide nanoparticles of spherical shape: Atangana-Baleanu fractional model', Numerical Methods for Partial Differential Equations, vol. 34, no. 5, pp. 1472-1488.View/Download from: UTS OPUS or Publisher's site
© 2017 Wiley Periodicals, Inc. The impact of magnetic field on Engine Oil based generalized Brinkman-type nanofluid over an oscillating vertical plate embedded in a porous medium is studied. Molybdenum Disulphide (MoS2) nanoparticles of spherical shape are suspended in Engine Oil, taken as conventional base fluid. Effect of thermal radiation in energy equation is also considered. A generalized model of Brinkman-type fluid is considered with newly introduced fractional derivatives known as Atangana-Baleanu Derivative (ABD) in the presence of heat transfer due to convection. Exact solution of the problem is determined by means of the Laplace transform. Expressions for velocity and temperature are obtained in terms of Mittag-Leffler and General Wright function. The effects of various pertinent parameters on velocity are portrayed and discussed graphically. Numerical results of rate of heat transfer are computed in tabular form. Which showed that increasing values of volume fraction and Prandtl number increase rate of heat transfer.
Khan, I, Saqib, M & Ali, F 2018, 'Application of the modern trend of fractional differentiation to the MHD flow of a generalized Casson fluid in a microchannel: Modelling and solution⋆', European Physical Journal Plus, vol. 133, no. 7.View/Download from: UTS OPUS or Publisher's site
© 2018, Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature. The motivation for writing this article is based on the contributions of Atangana and Baleanu to the fractal and fractional differentiation. Recently, Atangana and Baleanu launched a new fractional operator, namely, the Atangana-Baleanu fractional operator with the Mettang-Leffler function as the kernel of integration. This new operator is an efficient tool to model complex and real-world problems. This article deals with modeling and solution of the generalized magnetohydrodynamic (MHD) flow of a Casson fluid in a microchannel. This microchannel is taken of infinite length in the vertical direction and of finite width in the horizontal direction. The flow is modeled in terms of a set of partial differential equations involving the Atnagana-Baleanu time fractional operator along with physical initial and boundary conditions. The partial differential equations are transformed to ordinary differential equations via the fractional Laplace transformation and are solved for an exact solution using the transformed conditions. To explore the physical significance of various pertinent parameters affecting the flow, the numerical techniques of Zakian and Tzou are utilized for inversion of the Laplace transformation. The results obtained here may have useful industrial and engineering applications.
Saqib, M, Ali, F, Khan, I & Sheikh, NA 2018, 'Heat and mass transfer phenomena in the flow of Casson fluid over an infinite oscillating plate in the presence of first-order chemical reaction and slip effect', Neural Computing and Applications, vol. 30, no. 7, pp. 2159-2172.View/Download from: Publisher's site
© 2016, The Natural Computing Applications Forum. The objective of this article is to study the physics of slip effect at the boundary of a vertical plate in starting the flow of Casson fluid with the combined effect of radiative heat and mass transfer in the presence of first-order chemical reaction. The problem has been modeled in terms of partial differential equations along with appropriate initial and boundary conditions. The dimensionless governing equations have been solved by means of the Laplace transform technique. Exact solutions have been obtained for velocity, temperature and concentration profiles. The obtained velocity has been computed in tabular form for steady and transient velocities. The physics of velocity profile has been studied for various physical parameters through numerical computation and displayed in graphs. From obtained solutions, the well-known published results in the open literature have been recovered and displayed in graphs and tables.
Saqib, M, Ali, F, Khan, I, Sheikh, NA, Jan, SAA & Samiulhaq 2018, 'Exact solutions for free convection flow of generalized Jeffrey fluid: A Caputo-Fabrizio fractional model', Alexandria Engineering Journal, vol. 57, no. 3, pp. 1849-1858.View/Download from: Publisher's site
© 2017 Faculty of Engineering, Alexandria University The present article reports the applications of Caputo-Fabrizio time-fractional derivatives. This article generalizes the idea of free convection flow of Jeffrey fluid over a vertical static plate. The free convection is caused due to the temperature gradient. Therefore, heat transfer is considered for free convection. The classical model for Jeffrey fluid is written in dimensionless form with the help of non-dimensional variables. Furthermore, the dimensionless model is converted into a fractional model called as a generalized Jeffrey fluid model. The governing equations of generalized Jeffrey fluid model have been solved analytically using the Laplace transform technique. The recovery of existing solutions in the open literature is possible through this work in terms of classical Jeffrey fluid, fractional Newtonian fluid as well as classical Newtonian fluid. For various embedded parameters, the physics of velocity and temperature profiles is studied by means of numerical computation. This report provides a detailed discussion as well as a graphical representation of the obtained results.
Saqib, M, Saleem, MM, Mazhar, N, Awan, SU & Khan, US 2018, 'Design and analysis of a high-gain and robust multi-DOF electro-thermally actuated MEMS gyroscope', Micromachines, vol. 9, no. 11.View/Download from: UTS OPUS or Publisher's site
© 2018 by the authors. This paper presents the design and analysis of a multi degree of freedom (DOF) electro-thermally actuated non-resonant MEMS gyroscope with a 3-DOF drive mode and 1-DOF sense mode system. The 3-DOF drive mode system consists of three masses coupled together using suspension beams. The 1-DOF system consists of a single mass whose motion is decoupled from the drive mode using a decoupling frame. The gyroscope is designed to be operated in the flat region between the first two resonant peaks in drive mode, thus minimizing the effect of environmental and fabrication process variations on device performance. The high gain in the flat operational region is achieved by tuning the suspension beams stiffness. A detailed analytical model, considering the dynamics of both the electro-thermal actuator and multi-mass system, is developed. A parametric optimization is carried out, considering the microfabrication process constraints of the Metal Multi-User MEMS Processes (MetalMUMPs), to achieve high gain. The stiffness of suspension beams is optimized such that the sense mode resonant frequency lies in the flat region between the first two resonant peaks in the drive mode. The results acquired through the developed analytical model are verified with the help of 3D finite element method (FEM)-based simulations. The first three resonant frequencies in the drive mode are designed to be 2.51 kHz, 3.68 kHz, and 5.77 kHz, respectively. The sense mode resonant frequency is designed to be 3.13 kHz. At an actuation voltage of 0.2 V, the dynamically amplified drive mode gain in the sense mass is obtained to be 18.6 μm. With this gain, a capacitive change of 28.11 f F and 862.13 f F is achieved corresponding to the sense mode amplitude of 0.15 μm and 4.5 μm at atmospheric air pressure and in a vacuum, respectively.
Sheikh, NA, Ali, F, Khan, I & Saqib, M 2018, 'A modern approach of Caputo–Fabrizio time-fractional derivative to MHD free convection flow of generalized second-grade fluid in a porous medium', Neural Computing and Applications, vol. 30, no. 6, pp. 1865-1875.View/Download from: Publisher's site
© 2016, The Natural Computing Applications Forum. The present analysis represents the concept of the Caputo–Fabrizio derivatives of fractional order to MHD flow of a second-grade fluid together with radiative heat transfer. The fluid flow is subjected to an infinite oscillating vertical plate embedded in a saturated porous media. The fluid starts motion due to an oscillating boundary and temperature difference between the plate and the fluid. The problem is modeled in terms of partial differential equations, which consist of momentum equation and heat equation. The Laplace transform method is used to obtain the closed-form solutions for velocity and temperature profiles. In order to understand the physics of the problem under consideration, numerical results are obtained using Mathcad software and brought into light through graphical representations. The influence of various physical parameters is studied and displayed in various figures. The corresponding skin friction coefficient and Nusselt number are provided in tables. A graphical comparison is provided showing a strong agreement with the published results in the open literature.
Ali, F, Aamina, B, Khan, I, Sheikh, NA & Saqib, M 2017, 'Magnetohydrodynamic flow of brinkman-type engine oil based MoS2-nanofluid in a rotating disk with hall effect', International Journal of Heat and Technology, vol. 35, no. 4, pp. 893-902.View/Download from: Publisher's site
Nanotechnology currently has an important role in reducing engine wear and improving fuel efficiency within engines using nanoparticles in engine oil. Therefore, the work reported in this paper, aims to investigate the magnetohydrodynamic (MHD) flow of Brinkman-type Engine Oil-based Molybdenum disulfide (MoS2) nanofluid (BEOBMN) in a rotating frame along with Hall effect and thermal radiation. The problem is modeled in terms of partial differential equations with physical initial and boundary conditions. The Laplace transform technique is used to evaluate the exact solutions for velocity and temperature profiles. Graphical results are obtained through a computational software Mathcad and discussed for various embedded parameters. The Skin-friction and Nusselt number are computed in the tabular form and it is noticed that the rate of heat transfer enhances 6.35% by adding MoS2 in engine oil which improved its lubrication.
Ali, F, Sheikh, NA, Saqib, M & Khan, I 2017, 'Unsteady MHD flow of second-grade fluid over an oscillating vertical plate with isothermal temperature in a porous medium with heat and mass transfer by using the Laplace transform technique', Journal of Porous Media, vol. 20, no. 8, pp. 671-690.View/Download from: Publisher's site
© 2017 by Begell House, Inc. www.begellhouse.com. A problem describing the oscillating flow of an incompressible magnetohydrodynamic second-grade fluid in a porous medium with combined effect of heat and mass transfer in the presence of radiation is investigated. Exact solutions for cosine oscillations are obtained via the Laplace transform method. The obtained starting solutions are explicitly expressed as the sum of steady state and transient solutions. It is shown that previous results for a nonporous medium and hydrodynamic fluid are the limiting cases of the present problem. The effects of different parameters for velocity are plotted and discussed physically.
Kang, SM, Ali, A, Saqib, M & Nazeer, W 2017, 'New fifth and sixth order iteration schemes for solving nonlinear equations', Far East Journal of Mathematical Sciences, vol. 101, no. 11, pp. 2475-2488.View/Download from: Publisher's site
© 2017 Pushpa Publishing House, Allahabad, India. In this paper, we have introduced and analyzed two new algorithms of fifth and sixth order convergence. We have used modified homotopy perturbation technique to develop our algorithms. Convergence analysis of newly introduced algorithms has been discussed. To see efficiency and performance of these algorithms, we have made comparison of these algorithms with some well known algorithms exist in literature.
Kwun, YC, Saqib, M, Nazeer, W & Kang, SM 2017, 'Some convergence results for modified iteration schemes', Far East Journal of Mathematical Sciences, vol. 102, no. 1, pp. 223-234.View/Download from: Publisher's site
© 2017 Pushpa Publishing House, Allahabad, India. Some strong convergence results for modified Jungck Mann and modified Jungck Ishikawa iteration schemes have been established in a Banach space.
Saqib, M, Hasnain, S & Mashat, DS 2017, 'Highly Efficient Computational Methods for Two Dimensional Coupled Nonlinear Unsteady Convection-Diffusion Problems', IEEE Access, vol. 5, pp. 7139-7148.View/Download from: Publisher's site
© 2013 IEEE. In this paper, a numerical solution of 2-D time-dependent coupled nonlinear system is discussed. Both Crank-Nicholson and alternating direction implicit methods were used to address the problems associated with nonlinear system. These schemes depict the second-order accuracy in space and time. Moreover, system of these equations that is concerned with the implicit scheme is very efficient and reliable for solving 2-D nonlinear coupled convection diffusion equations. In this system, algebraic difference equations are solved at each time level. In fact, in this paper, these methodologies were unified with iterative methods to resolve nonlinear systems. The procedures have been analyzed for their stability and convergence. Numerical results showed that the proposed alternating direction implicit scheme was very efficient and reliable for solving 2-D nonlinear coupled convection diffusion equations. The proposed methods can be implemented for fixing nonlinear problems arising in engineering and physics.
Sheikh, NA, Ali, F, Khan, I, Gohar, M & Saqib, M 2017, 'On the applications of nanofluids to enhance the performance of solar collectors: A comparative analysis of Atangana-Baleanu and Caputo-Fabrizio fractional models', European Physical Journal Plus, vol. 132, no. 12.View/Download from: Publisher's site
© 2017, Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature. In the modern era, solar energy has gained the consideration of researchers to a great deal. Apparently, the reasons are twofold: firstly, the researchers are concerned to design new devices like solar collectors, solar water heaters, etc. Secondly, the use of new approaches to improve the performance of solar energy equipment. The aim of this paper is to model the problem of the enhancement of heat transfer rate of solar energy devices, using nanoparticles and to find the exact solutions of the considered problem. The classical model is transformed to a generalized model using two different types of time-fractional derivatives, namely the Caputo-Fabrizio and Atangana-Baleanu derivatives and their comparative analysis has been presented. The solutions for the flow profile and heat transfer are presented using the Laplace transform method. The variation in the heat transfer rate has been observed for different nanoparticles and their different volume fractions. Theoretical results show that by adding aluminum oxide nanoparticles, the efficiency of solar collectors may be enhanced by 5.2%. Furthermore, the effect of volume friction of nanoparticles on velocity distribution has been discussed in graphical illustrations. The solutions are reduced to the corresponding classical model of nanofluid.
Sheikh, NA, Ali, F, Khan, I, Saqib, M & Khan, A 2017, 'MHD Flow of Micropolar Fluid over an Oscillating Vertical Plate Embedded in Porous Media with Constant Temperature and Concentration', Mathematical Problems in Engineering, vol. 2017.View/Download from: Publisher's site
Copyright © 2017 Nadeem Ahmad Sheikh et al. The present analysis represents the MHD flow of micropolar fluid past an oscillating infinite vertical plate embedded in porous media. At the plate, free convections are caused due to the differences in temperature and concentration. Therefore, the combined effect of radiative heat and mass transfer is taken into account. Partial differential equations are used in the mathematical formulation of a micropolar fluid. The system of dimensional governing equations is reduced to dimensionless form by means of dimensional analysis. The Laplace transform technique is applied to obtain the exact solutions for velocity, temperature, and concentration. In order to highlight the flow behavior, numerical computation and graphical illustration are carried out. Furthermore, the corresponding skin friction and wall couple stress are calculated.
Sheikh, NA, Ali, F, Saqib, M, Khan, I & Jan, SAA 2017, 'A comparative study of Atangana-Baleanu and Caputo-Fabrizio fractional derivatives to the convective flow of a generalized Casson fluid', European Physical Journal Plus, vol. 132, no. 1.View/Download from: Publisher's site
© 2017, Società Italiana di Fisica and Springer-Verlag Berlin Heidelberg. Based on exponential kernel, Caputo and Fabrizio suggested a new definition for fractional order derivatives in 2015. Recently, in 2016, Atangana and Baleanu proposed another version of fractional derivatives, which uses the generalized Mittag-Leffler function as the non-singular and non-local kernel. Moreover, the Atangana-Balaenu (AB) version has all properties of fractional derivatives. Therefore, this articles aims to use the AB fractional derivative idea for the first time to study the free convection flow of a generalized Casson fluid due to the combined gradients of temperature and concentration. Hence, heat and mass transfer are considered together. For the sake of comparison, this problem is also solved via the Caputo-Fabrizio (CF) derivatives technique. Exact solutions in both cases (AB and CF derivatives) are obtained via the Laplace transform and compared graphically as well as in tabular form. In the case of AB approach, the influence of pertinent parameters on velocity field is displayed in plots and discussed. It is found that for unit time, the velocities obtained via AB and CF derivatives are identical. Velocities for time less than 1 show little variation and, for time higher than 1, this variation increases.
Sheikh, NA, Ali, F, Saqib, M, Khan, I, Jan, SAA, Alshomrani, AS & Alghamdi, MS 2017, 'Comparison and analysis of the Atangana–Baleanu and Caputo–Fabrizio fractional derivatives for generalized Casson fluid model with heat generation and chemical reaction', Results in Physics, vol. 7, pp. 789-800.View/Download from: Publisher's site
© 2017 The Authors Atangana and Baleanu (AB) in their recent work introduced a new version of fractional derivatives which uses the generalized Mittag-Leffler function as the non-singular and non-local kernel and accepts all properties of fractional derivatives. This articles aims to apply the AB fractional derivative to free convection flow of generalized Casson fluid due to the combined gradients of temperature and concentration with heat generation and first order chemical reaction. For the sake of comparison, this problem is also solved via Caputo-Fabrizio (CF) derivative technique. Exact solutions in both cases of AB and CF derivatives are obtained via Laplace transform and compared graphically as well as in tabular form. In the case of AB approach, the influence of pertinent parameters on velocity field is displayed in plots and discussed. It is found that for a unit time, the velocities obtained via AB and CF derivatives are identical. Velocities for the time less than 1 show little variation and for time bigger than 1, this variation increases.
Arif, M, Saqib, M, Basalamah, S & Naeem, A 2012, 'Counting of moving people in the video using neural network system', Life Science Journal, vol. 9, no. 3, pp. 1384-1392.
Automatic counting of people in the crowd using surveillance visual camera is very useful in effective crowd management, security surveillance, and many more applications. In this paper, we have proposed an intelligent framework to automate the process of people counting in the surveillance video. Foreground (moving people) segmentation from the video is done by combination of different foreground estimation techniques. Texture analysis and foreground pixel area for different segmentation techniques are used to extract the useful features. Neural Network is trained on these features and people counting accuracy of more than 96% is achieved on a benchmark video.
Kashif, SAR & Saqib, MA 2012, 'A neuro fuzzy application: Soft starting of induction motors with reduced energy losses', Electric Power Components and Systems, vol. 40, no. 12, pp. 1339-1350.View/Download from: Publisher's site
Soft starters are used in electrical drives for the smooth starting of blowers, fans, mixers, crushers, grinders, and pumps, as well as in many other modern industrial applications. This article presents a soft starter that reduces energy losses during the start-up process of an induction motor. A sensor-less technique has been used to enhance the response of the system. The artificial neural networks, used in the soft starter, have been compared for the estimation of different parameters. The adaptive neuro fuzzy inference system has been developed to control the speed and torque of the motor with the constraint of reduction in energy losses during the start-up process. A neural network implements the feedback estimator, thus eliminating the need for slow mechanical sensors, while the adaptive neuro fuzzy inference system with the help of artificial neural network estimators adjusts the firing angles of the thyristors (of an AC voltage controller) under different loading conditions. The control system has been implemented using a TMS320F2812 (Texas Instruments, Texas, USA) processor. The presented approach can be employed for both the off-line and on-line trainings and, hence, can solve the problem of on-line computation of firing angles. © 2012 Copyright Taylor and Francis Group, LLC.
Adeel, MS & Saqib, MA 2011, 'An adaptive scheme for power-related measurements and power-factor correction', Australian Journal of Electrical and Electronics Engineering, vol. 8, no. 3, pp. 211-218.View/Download from: Publisher's site
This paper presents a fast, low cost and accurate instrumentation scheme for powerrelated measurements and power-factor correction. These measurements include the root-meansquare values of current and voltage, the active and reactive powers, the total harmonic distortion and the true power factor. It is a microcontroller-based digital sampling system which runs a fast algorithm for displacement power factor measurement. The controlling system monitors and senses any variations in power factor, and accordingly switches the appropriate capacitor combination across the load. The scheme presents an economical and efficient solution to the power distribution companies for its customers. © Institution of Engineers Australia, 2011.
Kashif, SAR, Saqib, MA & Zia, S 2011, 'Implementing the induction-motor drive with four-switch inverter: An application of neural networks', Expert Systems with Applications, vol. 38, no. 9, pp. 11137-11148.View/Download from: Publisher's site
This paper reports a four switch based three-phase voltage source inverter using space vector pulse width modulation (SVPWM), and designed with a three-layer feed forward back propagation based artificial neural network (ANN). The input-output samples, obtained using simulations in Matlab Simulink, were used for the extensive training of the neural network. Matlab interface with National Instruments' NI-USB-6259 BNC was used for implementing the designed scheme with calculated weights and biases. The designed ANN based SVPWM model receives command voltage and reference speed as the inputs and generates pulse width modulated waves for the four-switch three-phase inverter bridge. The V/f ratio can be controlled by controlling the input parameters of the ANN generating PWM pulses. The simulations and experimental results, and harmonic analysis with the designed ANN structure are presented at different base speeds. The designed model was tested in under modulation, over modulation and unity modulation mode of operation and tuned to give minimum total harmonic distortion. Harmonic results at different modulation indexes are also presented. The ANN based implementation reduces the complexity of control system and overall cost reduction is achieved by the combination of FSTPI and ANN. © 2011 Elsevier Ltd. All rights reserved.
Saqib, MA, Stokes, AD, James, BW & Falconer, IS 2011, 'Electron temperature and arc diameter in a sand-filled HBC fuse', IEEE Transactions on Plasma Science, vol. 39, no. 7, pp. 1619-1630.View/Download from: Publisher's site
The electron temperature as a function of time in a model high-breaking-capacity fuse has been determined from measurement of the relative intensity of the Si II spectral lines at 505, 597, and 636 nm. The fuses used in this paper consisted of a 0.55-mm-diameter Ag wire fusible element surrounded by silica (SiO2) sand. The spectra were resolved with a grating spectrometer and recorded by a gated image intensifier coupled to a linear photodiode array for prospective currents of 1.25-and 4.5-kA amplitudes and for arc lengths of 112 and 240 mm. The electron temperatures varied during the life of the arc from no significant change (for 1.25-kA peak prospective current through the long fuse) to ∼50% decrease (for 4.5-kA peak prospective current through the short fuse). Average temperatures, excluding data points at the early and late times during the arc discharge when the most extreme temperatures were measured, were as follows: 1.8 ×104 K and 1.1 ×104 K at 1.25-and 4.5-kA peak prospective currents, respectively, for the 112-mm fuse and 1.4 ×104 K and 1.5 ×104 K at 1.25-and 4.5-kA peak prospective currents, respectively, for the 240-mm fuse. The individual data points, however, exhibited a wide scatter about the line of best fit. Detailed analysis of the data indicates that it is essential to include the intensity of all of the doublets previously listed when measuring the plasma electron temperature and that self-absorption at 636 nm is, at least for the present experiment, not a source of error. The measured electron temperatures were used to calculate the Spitzer conductivity of the plasma which, together with the measured electrical characteristics of the arc, enabled the variation of the diameter of the arc over time to be estimated. © 2011 IEEE.
Saqib, MA & Stokes, AD 2010, 'Arc behavior and confinement in a high-voltage, high breaking capacity fuse filler', IEEE Transactions on Power Delivery, vol. 25, no. 1, pp. 212-220.View/Download from: Publisher's site
This paper presents the results of arc investigation for a number of materials when they were used as high breaking capacity (HBC) fuse fillers. Aluminum hydro-oxide, boric acid, zinc oxide, titanium oxide, and boron trioxide have been investigated and their prospects as filling media in high-voltage, high breaking capacity fuses have been explored. The results of these tests are compared with those on silica sand at high currents. This study demonstrates that silica sand is a far superior filler in HBC fuses for heavy current interruption than the compounds tested. © 2009 IEEE.
Saqib, M, Daud Khan, S, Sharma, N, Scully-Power, P, Butcher, P, Colefax, A & Blumenstein, M 2019, 'Real-Time Drone Surveillance and Population Estimation of Marine Animals from Aerial Imagery', International Conference Image and Vision Computing New Zealand.View/Download from: UTS OPUS or Publisher's site
© 2018 IEEE. Video analysis is being rapidly adopted by marine biologists to asses the population and migration of marine animals. Manual analysis of videos by human observers is labor intensive and prone to error. The automatic analysis of videos using state-of-the-art deep learning object detectors provides a cost-effective way for the study of marine animals population and their ecosystem. However, there are many challenges associated with video analysis such as background clutter, illumination, occlusions, and deformation. Due to the high-density of objects in the images and sever occlusion, current state-of-the-art object often results in multiple detections. Therefore, customized Non-Maxima-Suppression is proposed after the detections to suppress false positives which significantly improves the counting and mean average precision of the detections. An end-to-end deep learning framework of Faster-RCNN  was adopted for detections with base architectures of VGG16 , VGGM  and ZF .
Saqib, M, Daud Khan, S, Sharma, N & Blumenstein, M 2017, 'Extracting descriptive motion information from crowd scenes', International Conference Image and Vision Computing New Zealand, International Conference on Image and Vision Computing New Zealand, IEEE, Christchurch, New Zealand, pp. 1-6.View/Download from: UTS OPUS or Publisher's site
© 2017 IEEE. An important contribution that automated analysis tools can generate for management of pedestrians and crowd safety is the detection of conflicting large pedestrian flows: this kind of movement pattern, in fact, may lead to dangerous situations and potential threats to pedestrian's safety. For this reason, detecting dominant motion patterns and summarizing motion information from the scene are inevitable for crowd management. In this paper, we develop a framework that extracts motion information from the scene by generating point trajectories using particle advection approach. The trajectories obtained are then clustered by using unsupervised hierarchical clustering algorithm, where the similarity is measured by the Longest Common Sub-sequence (LCS) metric. The achieved motions patterns in the scene are summarized and represented by using color-coded arrows, where speeds of the different flows are encoded with colors, the width of an arrow represents the density (number of people belonging to a particular motion pattern) while the arrowhead represents the direction. This novel representation of crowded scene provides a clutter free visualization which helps the crowd managers in understanding the scene. Experimental results show that our method outperforms state-of-the-art methods.
Saqib, M, Khan, SD, Sharma, N & Blumenstein, M 2018, 'Person Head Detection in Multiple Scales Using Deep Convolutional Neural Networks', Proceedings of the International Joint Conference on Neural Networks, International Joint Conference on Neural Networks, IEEE, Rio de Janeiro, Brazil.View/Download from: UTS OPUS or Publisher's site
© 2018 IEEE. Person detection is an important problem in computer vision with many real-world applications. The detection of a person is still a challenging task due to variations in pose, occlusions and lighting conditions. The purpose of this study is to detect human heads in natural scenes acquired from a publicly available dataset of Hollywood movies. In this work, we have used state-of-the-art object detectors based on deep convolutional neural networks. These object detectors include region-based convolutional neural networks using region proposals for detections. Also, object detectors that detect objects in the single-shot by looking at the image only once for detections. We have used transfer learning for fine-tuning the network already trained on a massive amount of data. During the fine-tuning process, the models having high mean Average Precision (mAP) are used for evaluation of the test dataset. Experimental results show that Faster R-CNN  and SSD MultiBox  with VGG16  perform better than YOLO  and also demonstrate significant improvements against several baseline approaches.
Das, A, Sengupta, A, Saqib, M, Pal, U & Blumenstein, M 2018, 'More Realistic and Efficient Face-Based Mobile Authentication using CNNs', Proceedings of the International Joint Conference on Neural Networks, International Joint Conference on Neural Networks, IEEE, Rio de Janeiro, Brazil, pp. 1-8.View/Download from: UTS OPUS or Publisher's site
© 2018 IEEE. In this work, we propose a more realistic and efficient facebased mobile authentication technique using CNNs. This paper discusses and explores an inevitable problem of using face images for mobile authentication, taken from varying distances with a front/selfie camera of the mobile phone. Incidentally, once an individual comes towards a certain distance from the camera, the face images get large and appear over-sized. Simultaneously sharp features of some portions of the face, such as forehead, cheek, and chin are changed completely. As a result, the face features change and the impact increases exponentially once the individual crosses a certain distance and gradually approaches towards the front camera. This work proposes a solution (achieving better accuracy and facial features, whereby face images were cropped and aligned around its close bounding box) to mitigate the aforementioned identified gap. The work investigated different frontier face detection and recognition techniques to justify the proposed solution. Among all the employed methods evaluated, CNNs worked best. For a quantitative comparison of the proposed method, manually cropped face images/annotations of the face images along with their close boundary were prepared. In turn, we have developed a database considering the above-mentioned scenario for 40 individuals, which will be publicly available for academic research purposes. The experimental results achieved indicate a successful implementation of the proposed method and the performance of the proposed technique is also found to be superior in comparison to the existing state-of-the-art.
Coluccia, A, Ghenescu, M, Piatrik, T, De Cubber, G, Schumann, A, Sommer, L, Klatte, J, Schuchert, T, Beyerer, J, Farhadi, M, Amandi, R, Aker, C, Kalkan, S, Saqib, M, Sharma, N, Makkah, SDK & Blumenstein, M 2017, 'Drone-vs-Bird detection challenge at IEEE AVSS2017', Proceedings of the 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017, IEEE International Conference on Advanced Video and Signal Based Surveillance, IEEE, Lecce, Italy, pp. 1-6.View/Download from: UTS OPUS or Publisher's site
© 2017 IEEE. Small drones are a rising threat due to their possible misuse for illegal activities, in particular smuggling and terrorism. The project SafeShore, funded by the European Commission under the Horizon 2020 program, has launched the 'drone-vs-bird detection challenge' to address one of the many technical issues arising in this context. The goal is to detect a drone appearing at some point in a video where birds may be also present: the algorithm should raise an alarm and provide a position estimate only when a drone is present, while not issuing alarms on birds. This paper reports on the challenge proposal, evaluation, and results1.
Saqib, M, Daud Khan, S, Sharma, N & Blumenstein, M 2017, 'A study on detecting drones using deep convolutional neural networks', Proceedings of the 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2017, IEEE International Conference on Advanced Video and Signal Based Surveillance, IEEE, Lecce, Italy.View/Download from: UTS OPUS or Publisher's site
© 2017 IEEE. The object detection is a challenging problem in computer vision with various potential real-world applications. The objective of this study is to evaluate the deep learning based object detection techniques for detecting drones. In this paper, we have conducted experiments with different Convolutional Neural Network (CNN) based network architectures namely Zeiler and Fergus (ZF), Visual Geometry Group (VGG16) etc. Due to sparse data available for training, networks are trained with pre-trained models using transfer learning. The snapshot of trained models is saved at regular interval during training. The best models having high mean Average Precision (mAP) for each network architecture are used for evaluation on the test dataset. The experimental results show that VGG16 with Faster R-CNN perform better than other architectures on the training dataset. Visual analysis of the test dataset is also presented.
Saqib, M, Khan, SD & Blumenstein, M 2016, 'Detecting dominant motion patterns in crowds of pedestrians', Proceedings of SPIE - The International Society for Optical Engineering, International Conference on Graphic and Image Processing, SPIE, Tokyo, Japan.View/Download from: UTS OPUS or Publisher's site
© 2017 SPIE. As the population of the world increases, urbanization generates crowding situations which poses challenges to public safety and security. Manual analysis of crowded situations is a tedious job and usually prone to errors. In this paper, we propose a novel technique of crowd analysis, the aim of which is to detect different dominant motion patterns in real-time videos. A motion field is generated by computing the dense optical flow. The motion field is then divided into blocks. For each block, we adopt an Intra-clustering algorithm for detecting different flows within the block. Later on, we employ Inter-clustering for clustering the flow vectors among different blocks. We evaluate the performance of our approach on different real-time videos. The experimental results show that our proposed method is capable of detecting distinct motion patterns in crowded videos. Moreover, our algorithm outperforms state-of-the-art methods.
Saqib, M, Khan, SD & Blumenstein, M 2016, 'Texture-based feature mining for crowd density estimation: A study', International Conference Image and Vision Computing New Zealand, International Conference on Image and Vision Computing New Zealand, IEEE, Palmerston North, New Zealand.View/Download from: UTS OPUS or Publisher's site
© 2016 IEEE. Texture feature is an important feature descriptor for many image analysis applications. The objectives of this research are to determine distinctive texture features for crowd density estimation and counting. In this paper, we have comprehensively reviewed different texture features and their different possible combinations to evaluate their performance on pedestrian crowds. A two-stage classification and regression based framework have been proposed for performance evaluation of all the texture features for crowd density estimation and counting. According to the framework, input images are divided into blocks and blocks into cells of different sizes, having varying crowd density levels. Due to perspective distortion, people appearing close to the camera contribute more to the feature vector than people far away. Therefore, features extracted are normalized using a perspective normalization map of the scene. At the first stage, image blocks are classified using multi-class SVM into different density level. At the second stage Gaussian Process Regression is used to re gress low-level features to count. Various texture features and their possible combinations are evaluated on publicly available dataset.
Kaleem, Z, Lee, CK, Saqib, M, Mohsin, S & Salim, F 2010, 'The way towards amplifier design using CAD (ADS) tool', International Conference on Advanced Communication Technology, ICACT, pp. 962-967.
This paper mainly focuses on design arts and operational mechanism of ADS tool. ADS tool is characterized by reliable, efficient and controlled functioning as compare to conventional approaches. In this paper, we describe an ADS tool based interactive procedure that provides the students in electrical and computer engineering programs with an easy-to-use reference and overview of an amplifier design. This multimedia-based system covers topics that start with introductory basic concepts in amplifier design and conclude with advanced and detailed concepts using the ADS tool.
Saqib, M & Lee, C 2010, 'Traffic control system using wireless sensor network', International Conference on Advanced Communication Technology, ICACT, pp. 352-357.
The Real time locating system (RTLS) determines and tracks the location of assets and people. This paper presents a novel application to estimate the position and velocity of vehicle using wireless sensor network. Two Anchor nodes are used as reader along roadside and total distance between them is known. Whenever a moving vehicle with tag comes in between the common part of the operating range of two anchor nodes, exchange of information is done using Symmetric double sided two way ranging algorithm, which gives us position information. Using position information at several interval of time, velocity can be easily obtained. Position and velocity is obtained and displayed on base station. Kalman filtering is used to estimate the position and velocity from noisy measurements. Performance evaluation is done comparing vehicle position speed true values with experimental and estimated values.
Khan, A, Saqib, M & Kaleem, Z 2009, 'Functional unit level parallelism in RISC architecture', Proceedings of the 6th International Conference on Frontiers of Information Technology, FIT '09.View/Download from: Publisher's site
This paper presents the design and implementation of RISC processor having five stages pipelined architecture. Functional unit parallelism is exploited through the implementation of pipelining in five stages of RISC processor. The hazards which come to life due to parallelism are data, structural, and control hazards .In order to achieve the true benefits of the parallelism through pipelining; these hazards must be properly handled. The data hazards are solved using bypassing in which we forward the required value of the operand to the succeeding instruction. Structural hazards are solved by implementing three port register file so that two operand reading and one register writing can be performed in parallel without degrading the performance. Control hazards arise from Branch, Jump and Call instructions. To solve these problems, we insert automated NOP in stage2, stage3 and stage4. The processor designed is a fully functional processor which can execute any program including jump statements, switch statements, loops and subroutines which are the basic ingredients of any computer program. Copyright 2009 ACM.