Maria Siddiqua

Dr. Maria Siddiqua

Artificial Intelligence and Data Science, National University of Computer & Emerging Sciences - FAST ,Karachi, Karachi, Sindh, Pakistan
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
26 June 2023 in IEEE Access
Verified
Journal Article
Open access
MSMaria Siddiqua
Maria Siddiqua
samir brahimsamir brahim
samir brahim
NANaeem Akhter
Naeem Akhter
AZAneela Zameer
Aneela Zameer
JKJavaid Khurshid
Javaid Khurshid
Various vision-based tasks suffer from inaccurate navigation and poor performance due to inevitable problems, such as adverse weather conditions like haze, fog, rain, snow, and clouds affecting ground and aerial navigation, as well as underwater images being degraded with blue-green tones and mud affecting marine navigation. While most techniques in the literature are designed to restore only one or a few degradations using a single model, using separate architectures for each restoration process is computationally expensive. To address this, an all-in-one Multidomain Attention-based Conditional Generative Adversarial Network (MACGAN) is proposed to improve scene visibility for optimal ground, aerial, and marine navigation, using the same set of parameters across all domains. The MACGAN is a lightweight network with four encoder and decoder blocks and multiple attention blocks in between, which enhances the image restoration process by focusing on the most important features. The performance of MACGAN is compared qualitatively and quantitatively with various state-of-the-art image-to-image translation models, all-in-one adverse weather removal models, and single-effect removal models. Further, MACGAN is tested on real-world unseen image domains, such as smog, dust, fog, rain, snow, and lightning. The results demonstrate that MACGAN can improve scene visibility and has good generalizability. An ablation study is also conducted to assess the impact of the discriminator and attention blocks in MACGAN, and the results confirm the effectiveness of the proposed architecture, which includes a discriminator and three attention blocks.

21 March 2025 in Advances in Networks
Verified
Journal Article
Open access
PDF file
MUHAMMAD FURQAN ZIAMUHAMMAD FURQAN ZIA
MUHAMMAD FURQAN ZIA
MSMaria Siddiqua
Maria Siddiqua
Messaoud Ahmed OuameurMessaoud Ahmed Ouameur
Messaoud Ahmed Ouameur
MBMiloud Bagaa
Miloud Bagaa
FAFadi Al-turjman
Fadi Al-turjman
The rapid growth of urbanization and technological advancements have led to the rise of smart cities and smart homes, where the Internet of Things (IoT) plays a pivotal role. Smart homes enhance energy efficiency, security, and convenience through automated systems and interconnected devices. This survey provides a comprehensive review of smart home architectures, communication technologies, and applications, emphasizing their integration within smart city infrastructures. It explores key components such as sensors, controllers, and cloud-based platforms that enable seamless automation. Additionally, this paper discusses major challenges in smart home security, including privacy risks, cyber threats, and interoperability issues among IoT devices. Security concerns such as unauthorized access, data breaches, and denial-of-service attacks are analyzed, alongside strategies to mitigate these risks. The study also highlights the importance of secure communication protocols, authentication mechanisms, and encryption techniques to ensure the resilience of smart home systems. Furthermore, this survey examines emerging research directions in smart home technology, including AI-driven automation, energy-efficient systems, and blockchain-based security solutions. As smart homes continue to evolve, addressing these challenges will be crucial for their widespread adoption. This paper aims to serve as a valuable resource for researchers, developers, and policymakers seeking to enhance the security and functionality of smart homes within the broader framework of smart cities.

23 January 2024 in International Journal of Image and Graphics
Verified
Journal Article
Closed access
MSMaria Siddiqua
Maria Siddiqua
NANaeem Akhter
Naeem Akhter
AZAneela Zameer
Aneela Zameer
JKJavaid Khurshid
Javaid Khurshid

26 October 2021
Verified
Conference Paper
Closed access
MSMaria Siddiqua
Maria Siddiqua
NANaeem Akhter
Naeem Akhter
JKJavaid Khurshid
Javaid Khurshid
Removal of multiple weather-induced effects in a single image remains an open problem, although several methods addressing single effect removal have been proposed. We present a single method for removing multiple weather-induced effects that are fog, haze, rain streaks, and snowflakes. The proposed method is a unified model, based on context encoder and conditional generative adversarial network, with a single set of parameters. We demonstrate that our model is effective at improving visibility in weather degraded images. Though the training is done on synthetic data the model generalizes on real images during testing.

26 October 2021
Verified
Conference Paper
Closed access
MSMaria Siddiqua
Maria Siddiqua
NANaeem Akhter
Naeem Akhter
JKJavaid Khurshid
Javaid Khurshid
Understanding the underwater environment is important for navigation, surveillance, and exploration. The aim is to restore underwater images degraded by light absorption and scattering in water medium resulting in poor visibility, low brightness, and low contrast of the scene. In this paper, we introduce a network based on the image to image translation that is Contextual Conditional Generative Adversarial Network (CCGAN) and compare its performance with the available image to image translation models namely, Unsupervised Image Translation (UNIT), cycleGAN, Contrastive Unpaired Translation (CUT) and fastCUT qualitatively and quantitatively. Both supervised and unsupervised models are analyzed and we show that the proposed model outrun the alternatives.

30 December 2024 in International Journal of Emerging Engineering and Technology
Verified
Journal Article
Open access
PDF file
MSMaria Siddiqua
Maria Siddiqua
MUHAMMAD FURQAN ZIAMUHAMMAD FURQAN ZIA
MUHAMMAD FURQAN ZIA
This paper proposes a robust framework for reconstructing 2D human facial images from half-frontal views, primarily captured under low-quality surveillance conditions. A custom MATLAB-based Graphical User Interface (GUI) is developed to support the complete pipeline, including frame extraction, enhancement, and face reconstruction. Representative frames are extracted and enhanced for video inputs using one of three techniques: histogram equalization, contrast stretching, or logarithmic transformation. Reconstruction involves detecting a single eye from the half-frontal image, followed by horizontal flipping and concatenation to generate a symmetric full-frontal face. The reconstructed faces are validated using the Viola-Jones object detection algorithm to confirm the presence and alignment of facial features. Quantitative evaluation uses the Structural Similarity Index (SSIM) and Jaccard Index (JI) to measure image quality and geometric accuracy. The proposed method is tested on publicly available datasets and a custom-designed dataset reflecting real-world surveillance challenges such as low resolution and poor illumination. Experimental results demonstrate that the framework delivers accurate and visually coherent reconstructions with low computational overhead, making it suitable for real-time surveillance and facial analysis applications.