As a data science researcher with a passion for artificial intelligence, I am enthusiastic about the potential of self-learning machines to shape the future. I believe that AI has the power to accelerate progress in a variety of fields, and I am committed to exploring and advancing its capabilities through my research.
Over 5 years of experience in applying artificial intelligence techniques to image, text, speech, and video data.
Over 4 years of experience in conducting research in scientific laboratories.
Over 5 years of experience in teamwork and leadership roles.
Graduate Research & Teaching Assistant
Utah State University, Logan, Utah,
U.S
• As a Graduate Teaching Assistant, I have assisted professors in
conducting lectures, graded
course materials, provided assistance to students, and managed coursework on Canvas.
• As a Graduate Research Assistant, I have conducted research in the areas of
Fairness
in
AI, AI in Education, and Social Media Mining under the supervision of Professor Hamid
Karimi.
I am working at the Data Science and
Applications Lab under the supervision of Prof. Hamid Karimi.
Skills: Statistical Modeling · Scientific Research
· Pattern Recognition · Data Science · Artificial Intelligence (AI) · Data Analysis ·
Machine
Learning · Research and Development (R&D) · Teamwork · Deep Learning · Time Series
Analysis · Identifying New Opportunities · Scripting · Statistical Analysis · Diverse
Groups Of People · Design of Experiments (DOE) · Project Management · Python
(Programming Language) · Team Leadership
Research Associate
National Center of Artificial Intelligence, University of
Engineering & Technology
Peshawar, Pakistan
Performing data mining on satellite spectral image data through cloud-based computing is my primary job. My job included undertaking various tasks such as data collection, annotation, pipelining, pattern recognition, object detection, and segmentation, among others. These activities have diverse applications in fields such as environmental monitoring, land cover and land use classification, and geological exploration. Copernicus Article on my research
Project Engineer
U.S-Pakistan Center for Advanced Studies in Energy, Peshawar,
Pakistan
As a project engineer specializing in machine learning and data
analysis,
my primary responsibilities included:
Ph.D. Computer Science
Utah State University, Logan, Utah, U.S
Courses: Timeseries Analysis, Fairness AI, Probabilistic Modelling, Keystroke, Abstract Syntax Trees, Graph Neural Networks, Education Research
Publications: 1) Deciphering Student Coding Behavior: Interpretable Keystroke Features and Ensemble Strategies for Grade Prediction 2) Assessing the Promise and Pitfalls of ChatGPT for Automated Code Generation 3) A New Framework to Assess the Individual Fairness of Probabilistic Classifiers 4) An Analysis of the Dynamics of Ties on Twitter 5) Enhancing the Performance of Automated Grade Prediction in MOOC using Graph Representation Learning
Masters in Computer Engineering
University of Engineering & Technology
Peshawar, Pakistan
Courses: Remote Sensing, Pattern Recognition, Artificial Intelligence, Machine Learning Techniques, Evolutionary Computation, Optimization Techniques, Computational Bioinformatics
Bachelors in Computer Engineering
University of Engineering & Technology
Peshawar, Pakistan
Courses: Programming (OOP, Data Structures, System Programming), Digital Image Processing, Computer Organization & Architecture, Operating Systems, Circuits and Systems, Digital System Design, Microcontroller Based System Design, Wireless Communications, Database Management System etc
Years Worked
Publications
Projects Completed
Coffee Drinked
As a Machine Learning and Deep Learning expert with 7 certifications and 5 publications, I have a strong foundation in this field. My project experience includes a range of tasks such as anomaly detection in aircraft engines, image classification, object detection, object localization, image segmentation, and natural language processing. I have applied my skills to diverse data types including tabular, image, text, and video, and have developed efficient machine learning pipelines for various downstream applications. My expertise in this field is demonstrated by my successful projects and certifications.
I have been conducting research in the field of Machine Learning and Deep Learning since 2017. My research journey began with a focus on identifying the social and technical factors that contribute to the failure of micro-hydro power plants. As a project engineer, I was subsequently hired to work on prognosis and health monitoring of jet aircrafts using sensor data mining techniques. My research experience also includes a position as a research associate at the national research lab NCAI, where I published 3 articles on remote sensing data for geological mapping. Currently, as a Ph.D. candidate, I am engaged in a project on grade prediction using Abstract Syntax Tree and Graph Neural Networks.
Throughout my career, I have had the opportunity to mentor and supervise junior researchers and interns. In addition to my research pursuits, I have also taken on leadership roles outside of academia. For example, I co-founded a film production company called Rethinker Media with my brother, and I created an online community of more than 10k Google Earth Engine practitioners and researchers . I also founded and currently preside over the first Filmmaking Club at Utah State University, and I have served as an executive member of the Chitral Engineering and Doctors Association to promote higher education among minorities in Pakistan. These experiences have helped me to develop my leadership skills and capabilities.
PCIndFair: A New Framework to Assess the Individual Fairness of Probabilistic Classifiers
Speaker diarization (or diarization) is the process of partitioning an audio stream containing human speech into homogeneous segments according to the identity of each speaker. In this project, Speaker Diarization module by using the pre-trained model for creating speaker embeddings.
Keystroke data in programming reveals intricate patterns that reflect the behavior of programmers. These patterns hold promise for predicting grades and other applications, providing insights into the skills of both proficient and less proficient programmers. Analyzing these patterns can yield tailored feedback for students who need support, enabling effective interventions. Our study utilizes a keystroke dataset from the CS1 (Introduction to Computer Science) course at Utah State University. We developed novel features by combining elements like key presses, timestamps, source locations, and programming terminology, drawing on prior research, our insights, and an analysis of programming behavior. An ensemble-based feature selection method identifies key features, which are then used in hyperparameter optimization and grade prediction with six classification and three regression algorithms. We categorized grades into three levels: Low, Average, and High. Despite challenges such as class imbalance, plagiarism, limited data per assignment, and the ceiling effect, we attained a notable weighted F1 score of 78%. We also introduce an ensemble classification strategy, merging Isolation Forest outlier detection with a refined Random Forest classifier, achieving 80% accuracy on our test set. Additionally, we provide a detailed interpretation of our features, supported by results and a case study of our dataset. This research aims to enhance computer science education at the undergraduate level, focusing on improving its overall quality. Code and data are available https://github.com/DSAatUSU/Student-Coding-Behavior.git.
Read more
Online social networks are the breeding grounds for user connections, fostering information exchange, communication, content sharing, and community building. However, the dissolution of these digital relationships, often a less-explored facet, complements the studies of tie formation and maintenance. A comprehensive grasp of these connections, encompassing their inception, unraveling, and the potential foresight of disconnections, offers invaluable insights into network dynamics and the progression of interpersonal bonds. Yet, the investigation of broken ties faces a substantial challenge: the paucity of longitudinal and detailed data. To bridge this gap, this paper curates an expansive dataset, spanning over 120,000 Twitter users tracked across 15 weeks with weekly snapshots. Armed with this dataset, we embark on an extensive exploration of Twitter links, delving into five distinct categories within the Twitter social graph. These categories encompass structural features like centrality, content-related aspects, including post polarity, user profile attributes like verified status, egocentric network elements such as reciprocity, and dense user representations typified by node2vec. Subsequently, we conduct a thorough analysis of these diverse features to unveil meaningful patterns.
Read more
Fairness in machine learning has become a global concern due to the predominance of ML in automated decision-making systems. In comparison to group fairness, individual fairness, which aspires that similar individuals should be treated similarly, has received limited attention due to some challenges. One major challenge is the availability of a proper metric to evaluate individual fairness, especially for probabilistic classifiers. In this study, we propose a framework PCIndFair to assess the individual fairness of probabilistic classifiers. Unlike current individual fairness measures, our framework considers probability distribution rather than the final classification outcome, which is suitable for capturing the dynamic of probabilistic classifiers, e.g., neural networks. We perform extensive experiments on four standard datasets and discuss the practical benefits of the framework. This study can be helpful for machine learning researchers and practitioners flexibly assess their models' individual fairness.
Read more
Artificial intelligence (AI)-based multispectral remote sensing has been the best supporting tool using limited resources to enhance the lithological mapping abilities with accuracy, supported by ground truthing through traditional mapping techniques. The availability of the dataset, choice of algorithm, cost, accuracy, computational time, data labeling, and terrain features are some crucial considerations that researchers continue to explore. In this research, support vector machine (SVM) and artificial neural network (ANN) were applied to the Sentinel-2 MSI dataset for classifying lithologies having subtle compositional differences in the Kohat Basin's remote, inaccessible regions within Pakistan. First, we used principal component analysis (PCA), minimum noise fraction (MNF), and available maps for reliable data annotation for training SVM and (ANN) models for mapping ten classes (nine lithological units + water). The ANN and SVM results were compared with the previously conducted studies in the area and ground truth survey to evaluate their accuracy. SVM mapped ten classes with an overall accuracy (OA) of 95.78% and kappa coefficient of 0.95, compared to 95.73% and 0.95 by ANN classification. The SVM algorithm was more efficient concerning computational efficiency, accuracy, and ease due to available features within Google Earth Engine (GEE). Contrarily, ANN required time-consuming data transformation from GEE to Google Cloud before application in Google Colab.
Read more
Despite low spatial resolutions, thermal infrared bands (TIRs) are generally more suitable for mineral mapping due to their high penetration in vegetated areas compared to shortwave infrared (SWIR) bands. The weak combinations of SWIR bands for minerals can be compensated by fusing SWIR-bearing data (Sentinel-2 and Landsat-8) with other multispectral data containing fundamental tones from TIR bands. In this paper, marble in a granitic complex in Mardan District (Khyber Pakhtunkhwa) in Pakistan is discriminated by fusing feature-oriented principal component selection (FPCS) obtained from the ASTER, Landsat-8 Operational Land Imager (OLI), Thermal Infrared Sensor (TIRS) and Sentinel-2 MSI data. Cloud computing from Google Earth Engine (GEE) was used to apply FPCS before and after the decorrelation stretching of Landsat-8, ASTER, and Sentinel-2 MSI data containing five (5) bands in the Landsat-8 OLI and TIRS and six (6) bands each in the ASTER and Sentinel-2 MSI datasets, resulting in 34 components (i.e., 2 × 17 components). A weighted linear combination of selected three components was used to map granite and marble. The samples collected during field visits and petrographic analysis confirmed the remote sensing results by revealing the region’s precise contact and extent of marble and granite rock types. The experimental results reflected the theoretical advantages of the proposed approach compared with the conventional stacking of band data for PCA-based fusion. The proposed methodology was also applied to delineate granite deposits in Karoonjhar Mountains, Nagarparker (Sindh province) and the Kotah Dome, Malakand (Khyber Pakhtunkhwa Province) in Pakistan. The paper presents a cost-effective methodology by the fusion of FPCS components for granite/marble mapping during mineral resource estimation. The importance of SWIR-bearing components in fusion represents minor minerals present in granite that could be used to model the engineering properties of the rock mass.
Read more
