Naveed Ahmed

Ashish Jha, Dimitrii Ermilov, Konstantin Sobolev et al.

Pedestrian Attribute Recognition (PAR) focuses on identifying various attributes in pedestrian images, with key applications in person retrieval, suspect re-identification, and soft biometrics. However, Deep Neural Networks (DNNs) for PAR often suffer from over-parameterization and high computational complexity, making them unsuitable for resource-constrained devices. Traditional tensor-based compression methods typically factorize layers without adequately preserving the gradient direction during compression, leading to inefficient compression and a significant accuracy loss. In this work, we propose a novel approach for determining the optimal ranks of low-rank layers, ensuring that the gradient direction of the compressed model closely aligns with that of the original model. This means that the compressed model effectively preserves the update direction of the full model, enabling more efficient compression for PAR tasks. The proposed procedure optimizes the compression ranks for each layer within the ALM model, followed by compression using CPD-EPC or truncated SVD. This results in a reduction in model complexity while maintaining high performance.

Naveed Ahmed, Samuele Rubino

In this paper, we consider up-to-date and classical Finite Element (FE) stabilized methods for time-dependent incompressible flows. All studied methods belong to the Variational MultiScale (VMS) framework. So, different realizations of stabilized FE-VMS methods are compared in high Reynolds numbers vortex dynamics simulations. In particular, a fully Residual-Based (RB)-VMS method is compared with the classical Streamline-Upwind Petrov--Galerkin (SUPG) method together with grad-div stabilization, a standard one-level Local Projection Stabilization (LPS) method, and a recently proposed LPS method by interpolation. These procedures do not make use of the statistical theory of equilibrium turbulence, and no ad-hoc eddy viscosity modeling is required for all methods. Applications to the simulations of high Reynolds numbers flows with vortical structures on relatively coarse grids are showcased, by focusing on two-dimensional plane mixing-layer flows. Both Inf-Sup Stable (ISS) and Equal Order (EO) FE pairs are explored, using a second-order semi-implicit Backward Differentiation Formula (BDF2) in time. Based on the numerical studies, it is concluded that the SUPG method using both ISS and EO FE pairs performs best among all methods. Furthermore, there seems to be no reason to extend SUPG method by the higher order terms of the RB-VMS method.

Abdul Wahab, Tasawar Abbas, Naveed Ahmed et al.

In this article a topological sensitivity framework for far field detection of a diametrically small electromagnetic inclusion is established. The cases of single and multiple measurements of the electric far field scattering amplitude at a fixed frequency are taken into account. The performance of the algorithm is analyzed theoretically in terms of its resolution and sensitivity for locating an inclusion. The stability of the framework with respect to measurement and medium noises is discussed. Moreover, the quantitative results for signal-to-noise ratio are presented. A few numerical results are presented to illustrate the detection capabilities of the proposed framework with single and multiple measurements.

Muhammad Afzal, Naveed Ahmed, Volker John

A residual-based a posteriori error estimator is proposed for the incompressible Oseen problem in the convection-dominated regime. The SUPG/PSPG/grad-div stabilized finite element method is used as discretization. The error estimator estimates the global error in a norm that is used in the a priori error analysis of the method. Based on several hypotheses concerning the error and interpolation errors, the robustness of the estimator in the convection-dominated regime is proved. Numerical studies support the analytic results. Finally, the extension of the a posteriori error estimator to the steady-state Navier--Stokes equations is discussed.

Nizamuddin Maitlo, Nooruddin Noonari, Kaleem Arshid et al.

Recently, researchers have been exploring various ways to improve the effectiveness and efficiency of autonomous vehicles by researching new methods, especially for indoor scenarios. Autonomous Vehicles in indoor navigation systems possess many challenges especially the limited accuracy of GPS in indoor scenarios. Several, robust methods have been explored for autonomous vehicles in indoor scenarios to solve this problem, but the ineffectiveness of the proposed methods is the high deployment cost. To address the above-mentioned problems we have presented A low-cost indoor navigation method for autonomous vehicles called Affordable Indoor Navigation Solution (AINS) which is based on based on Monocular Camera. Our proposed solution is mainly based on a mono camera without relying on various huge or power-inefficient sensors to find the path, such as range finders and other navigation sensors. Our proposed method shows that we can deploy autonomous vehicles indoor navigation systems while taking into consideration the cost. We can observe that the results shown by our solution are better than existing solutions and we can reduce the estimated error and time consumption.

Mohammad Lataifeh, Xavier Carrasco, Ashraf Elnagar et al.

Recent advances in Generative Adversarial Networks (GANs) continue to attract the attention of researchers in different fields due to the wide range of applications devised to take advantage of their key features. Most recent GANs are focused on realism, however, generating hyper-realistic output is not a priority for some domains, as in the case of this work. The generated outcomes are used here as cognitive components to augment character designers creativity while conceptualizing new characters for different multimedia projects. To select the best-suited GANs for such a creative context, we first present a comparison between different GAN architectures and their performance when trained from scratch on a new visual characters dataset using a single Graphics Processing Unit. We also explore alternative techniques, such as transfer learning and data augmentation, to overcome computational resource limitations, a challenge faced by many researchers in the domain. Additionally, mixed methods are used to evaluate the cognitive value of the generated visuals on character designers agency conceptualizing new characters. The results discussed proved highly effective for this context, as demonstrated by early adaptations to the characters design process. As an extension for this work, the presented approach will be further evaluated as a novel co-design process between humans and machines to investigate where and how the generated concepts are interacting with and influencing the design process outcome.

Ulrich Wilbrandt, Clemens Bartsch, Naveed Ahmed et al.

{\sc ParMooN} is a program package for the numerical solution of elliptic and parabolic partial differential equations. It inherits the distinct features of its predecessor {\sc MooNMD} \cite{JM04}: strict decoupling of geometry and finite element spaces, implementation of mapped finite elements as their definition can be found in textbooks, and a geometric multigrid preconditioner with the option to use different finite element spaces on different levels of the multigrid hierarchy. After having presented some thoughts about in-house research codes, this paper focuses on aspects of the parallelization for a distributed memory environment, which is the main novelty of {\sc ParMooN}. Numerical studies, performed on compute servers, assess the efficiency of the parallelized geometric multigrid preconditioner in comparison with some parallel solvers that are available in the library {\sc PETSc}. The results of these studies give a first indication whether the cumbersome implementation of the parallelized geometric multigrid method was worthwhile or not.