Ishaq Ansari

Ishaq Ansari

Auto-generated profile, based on publicly available information

Ishaq Ansari

Department of Electrical and Computer Engineering, Texas AM University at Qatar, Ar-Rayyan, Qatar

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
23 March 2025 in Advances in Water Resources
Verified
Journal Article
Open access
MYMohammed Yaqoob
Mohammed Yaqoob
MAMohammed Yusuf Ansari
Mohammed Yusuf Ansari
MIMohammed Ishaq
Mohammed Ishaq
UAUnais Ashraf
Unais Ashraf
SPSaideep Pavuluri
Saideep Pavuluri
TSThomas D. Seers
Thomas D. Seers

29 July 2024 in IEEE Access
Verified
Journal Article
Open access
IAIshaq Ansari
Ishaq Ansari
AMAbubakr Mohammed
Abubakr Mohammed
YAYaqoob Ansari
Yaqoob Ansari
MAMohammed Yusuf Ansari
Mohammed Yusuf Ansari
SRSaquib Razak
Saquib Razak
EFEduardo Feo Flushing
Eduardo Feo Flushing
In our research, we address the problem of coordination and planning in heterogeneous multi-robot systems for missions that consist of spatially localized tasks. Conventionally, this problem has been framed as a task allocation problem that maps tasks to robots. However, all previous work assumes that tasks are atomic procedures. In this work, we relax this assumption and adopt a non-atomic model of tasks that enables robots to accomplish mission tasks incrementally over disjoint periods, precisely to account for the possibility of having a task serviced by numerous individual contributions over time. We propose a cooperative, load-balancing task allocation and scheduling algorithm based on sequential single-item auctions (CoLoSSI) that explicitly considers the non-atomicity of tasks, promotes synergies between agents, and enables cooperation while maintaining computational tractability. We also propose a fully distributed variant of CoLoSSI that tackles sparse, communication-restricted scenarios. Computational and simulation results confirm the efficacy of the proposed approaches for generating good-quality mission plans with low computational effort.

18 March 2025 in IEEE Access
Verified
Journal Article
Open access
MYMohammed Yaqoob
Mohammed Yaqoob
MAMohammed Yusuf Ansari
Mohammed Yusuf Ansari
MIMohammed Ishaq
Mohammed Ishaq
IJIssac Sujay Anand John Jayachandran
Issac Sujay Anand John Jayachandran
MHMohammed S. Hashim
Mohammed S. Hashim
TSThomas Daniel Seers
Thomas Daniel Seers
Morphological characterization of microcrystalline rock textures typically relies upon the visual interpretation and manual measurement of scanning electron microscopy (SEM) imagery: a practice fraught with subjectivity, inefficiency, sampling bias, and data loss.We introduce a state-of-the-art computer vision pipeline, built on deep learning architectures, for segmenting and classifying individual microcrystals from SEM images. Initially applied to low-Mg calcite carbonate rocks, instance segmentation is achieved using a custom-tuned version of Meta’s Segment Anything Model (SAM). To train and test the classifier, we utilized 48 SEM images of diverse carbonate microtextures composed of Low-Mg calcite from studies performed worldwide. Each individual microcrystal (1852 in total) was labelled according to a bipartite classification scheme, encompassing both crystal shape (rhombic, polyhedral, amorphous, and spherical), and degree of crystal facet definition (euhedral to subhedral, anhedral), with a total of four distinct classes. MicroCrystalNet: our proposed classification model employs a convolutional neural network architecture, incorporating advanced feature map processing (feature normalization, dimensionality reduction, and sparse feature selection), integrated within a novel Normalized Sparse Reduction block. Performance metrics reveal excellent average precision scores (AP = 0.93-0.98) and Area Under Receiver-Operator Curve values (AUC= 0.95-0.99) across all classes, with visual comparison to manual ground truth images demonstrating powerful inter-class discriminatory power, even in the presence of occlusions.

13 February 2024 in Earth and Space Science
Verified
Journal Article
Open access
IJIssac Sujay Anand John Jayachandran
Issac Sujay Anand John Jayachandran
HGHolly Catherine Gibbs
Holly Catherine Gibbs
JLJuan Carlos Laya
Juan Carlos Laya
YQYemna Qaiser
Yemna Qaiser
TKTalha Khan
Talha Khan
TSThomas Daniel Seers
Thomas Daniel Seers
Petrographic observations are vital for carbonate pore‐typing, linking geological frameworks to petrophysical behavior. However, current petrographic pore typing is manual, with the qualitative to semi‐quantitative results not easily fitted into quantitative subsurface characterization. Some recent studies have automated this process using supervised machine learning (ML) and deep learning (DL), focusing on simple pore morphological features, and have reported high classification accuracies for several complex pore types. However, there are concerns about the validity of these studies due to conceptual and technical flaws in their collective approach. This study was aimed at a more fundamental problem, classifying between open microfractures and open pores in petrographic thin sections using an object‐based approach and explainable supervised ML. We analyzed 18 carbonate thin sections from the USA, numerically representing them using five shape features: compactness, aspect ratio, extent, solidity, and formfactor. Using a labeled data set of 400 microfractures and 400 pores, we evaluated nine of the most widely used supervised models. All models showed high testing accuracies (89.58%–90.42%). Interestingly, complex non‐linear models did not significantly outperform simpler linear ones. Compactness and aspect ratio were the most informative features. However, the labeled data sets did not reflect the overall data set's complexity, which suggested that high accuracies in similar studies might be due to curated data sets rather than accounting for the true complexity of carbonate pore systems. The study concludes that simple shape features are ineffective for classifying carbonate pore types. It is hoped that this study will provide a foundation for more robust artificial intelligence‐assisted pore typing.

4 November 2020
Verified
Conference Paper
Closed access
IAIshaq Ansari
Ishaq Ansari
AMAbubakr Mohamed
Abubakr Mohamed
EFEduardo Feo Flushing
Eduardo Feo Flushing
SRSaquib Razak
Saquib Razak
In our research, we address the problem of coordination and planning in heterogeneous multi-robot systems for missions that consists of a set of spatially localized tasks. Conventionally, this problem has been framed as a task allocation problem that maps tasks to robots. However, all previous work assume that tasks are atomic procedures. In this work we relax this assumption and adopt a non-atomic model of tasks that enables robot accomplishing mission tasks in an incremental manner over disjoint periods of time, precisely to account for the possibility of having a task being serviced by multiple individual contributions over time. This model can be useful in search and rescue scenarios: the same portion of the environment can be explored at different times by different agents using different sensors. We propose a cooperative, load-balancing task allocation and scheduling algorithm based on sequential single-item auctions (CoLoSSI). Our approach explicitly considers the non-atomicity of tasks and promotes synergies between agents enabling cooperation while at the same time maintaining computational tractability. We also study a fully distributed implementation of the task allocation approach in sparse, communication-restricted scenarios, and propose an effective strategy to enhance its computational efficiency. A computational and simulation validation is also carried out, confirming the efficacy of the proposed approach for generating good quality mission plans with low computational effort.