Research Interest

        • Ph.D. from Gautam Buddha University, Greater Noida in 2014.
        • M.Tech. in Computer Science and Engineering from YMCAIE, Faridabad with 1st Division.
        • IBM Certified Database Associate (Candidate\Testing ID: PR1326592)
        • Honours Diploma from NIIT Technologies in Network-Centered Computing.
        • “Object-oriented analysis and design using with essentials of Rational software architect” Certified.
        • Qualified GATE with AIR Ranking 348.

      • Research Interests and Expertise

        Research Overview

        My research is primarily focused on the design, development and application of intelligent computational systems that can learn from experience, acquire knowledge, adapt to changing environments and make autonomous decisions with minimal human intervention. The central objective of my research is to advance the foundations of Artificial Intelligence and intelligent computing by developing efficient, scalable and reliable computational models capable of addressing complex real-world problems.

        My research lies at the intersection of Artificial Intelligence, Expert Systems, Machine Learning, Deep Learning and Soft Computing. I am particularly interested in developing intelligent algorithms that can automatically discover hidden patterns, extract meaningful information and transform large volumes of structured and unstructured data into actionable knowledge. My work emphasizes the integration of learning, reasoning, optimization and decision-making techniques to develop systems that are adaptive, robust and computationally efficient.

        In the contemporary data-driven era, the increasing volume, velocity and diversity of information have created significant challenges in knowledge extraction and intelligent decision-making. Conventional computational approaches often struggle with uncertainty, incomplete information, high-dimensional data and complex relationships among variables. My research addresses these challenges through advanced learning algorithms, knowledge-based methodologies and hybrid computational frameworks.

        A major thrust of my research is to develop learning systems that go beyond conventional pattern recognition. I investigate how computational models can autonomously identify suitable knowledge representations, discover meaningful relationships, distinguish genuine patterns from random variations and improve their performance through iterative learning. Particular attention is given to the integration of prior domain knowledge with data-driven learning to enhance model accuracy, reliability and interpretability.

        Another important dimension of my research is the development of explainable and trustworthy intelligent systems. I believe that the effectiveness of an intelligent system should not be measured solely by its predictive accuracy. Its ability to explain decisions, handle uncertainty, generalize to unseen data and operate within practical computational constraints is equally important. Accordingly, my research explores transparent learning methodologies and interpretable models that can support informed human decision-making.

        Core Research Domains

        1. Artificial Intelligence and Intelligent Systems

        My research explores the theoretical foundations and practical applications of Artificial Intelligence for developing autonomous and adaptive computational systems. This includes intelligent reasoning, knowledge acquisition, automated problem-solving and decision support. I am interested in developing systems that combine learning and reasoning capabilities to solve complex problems across diverse application domains.

        2. Expert Systems and Knowledge-Based Computing

        An important area of my research involves the development of knowledge-based systems that represent human expertise through structured rules, logical relationships and inference mechanisms. I investigate rule acquisition, knowledge representation, automated reasoning and the integration of expert knowledge with machine learning algorithms. The objective is to develop intelligent systems capable of making informed decisions even when training data is limited or incomplete.

        3. Machine Learning and Computational Learning Theory

        My research encompasses supervised, unsupervised and semi-supervised learning methodologies for classification, regression, clustering and predictive analytics. Particular emphasis is placed on understanding the learning process, selecting appropriate model representations and improving generalization. I also explore efficient learning strategies that can identify meaningful patterns while reducing computational complexity and minimizing overfitting.

        4. Deep Learning and Neural Computing

        I am interested in deep learning architectures and neural computational models for learning complex representations from large-scale datasets. Research directions include neural network optimization, feature extraction, representation learning and the application of deep architectures to image, video and text analysis. I am particularly interested in investigating the effectiveness of deep learning models under varying data availability and computational constraints.

        5. Soft Computing and Computational Intelligence

        My research in Soft Computing focuses on computational methodologies that can effectively handle imprecision, uncertainty and approximate reasoning. This includes fuzzy logic, evolutionary computation, probabilistic approaches and hybrid intelligent techniques. The objective is to develop flexible computational models capable of addressing problems where conventional deterministic approaches may be insufficient.

        6. Natural Language Processing and Text Analytics

        My research in Natural Language Processing focuses on enabling machines to understand, process and extract meaningful information from human language. Specific interests include automatic text summarization, information extraction, text classification, semantic analysis and intelligent document processing. I am particularly interested in developing computational techniques for transforming large volumes of textual information into concise and meaningful knowledge.

        7. Deepfake Detection and Digital Media Forensics

        With the rapid advancement of generative artificial intelligence, detecting manipulated digital content has become an important research challenge. My research explores machine learning and deep learning approaches for identifying manipulated images and videos. This includes the investigation of visual inconsistencies, learned representations, classification techniques and robust detection frameworks for digital media authenticity and information integrity.

        Emerging and Specialized Research Directions

        My ongoing and emerging research interests include the following specialized areas:

        • Automatic Representation Learning: Developing algorithms that can automatically identify suitable feature and knowledge representations during the learning process.
        • Rule-Based Machine Learning: Investigating methods for learning interpretable rules and structured decision models directly from data.
        • Probabilistic Learning: Designing models capable of reasoning under uncertainty and handling incomplete or noisy information.
        • Ensemble Learning: Combining multiple predictive models to improve accuracy, robustness and stability.
        • Hybrid Intelligent Systems: Integrating symbolic reasoning, statistical learning and computational intelligence within unified frameworks.
        • Explainable Artificial Intelligence: Developing transparent and interpretable models that provide meaningful explanations for their predictions.
        • Knowledge-Guided Learning: Incorporating prior knowledge, expert rules and domain constraints into machine learning processes.
        • Cost-Sensitive Learning: Developing classification and prediction algorithms that account for different costs associated with incorrect decisions.
        • Model Selection and Optimization: Investigating efficient techniques for selecting suitable algorithms, tuning parameters and preventing overfitting.
        • Scalable Machine Learning: Exploring subsampling, dimensionality reduction and computational optimization for large-scale learning problems.
        • Feature Selection and Dimensionality Reduction: Identifying relevant features while reducing data complexity and improving learning efficiency.
        • Trustworthy and Reliable AI: Addressing robustness, generalization, transparency and reliability in intelligent computational systems.
        • Generative Artificial Intelligence: Exploring emerging generative models and their applications in intelligent content generation, representation learning and knowledge discovery.
        • Multimodal Learning: Investigating computational frameworks that integrate information from text, images, video and other heterogeneous data sources.

        Research Methodologies

        My research adopts a multidisciplinary computational approach combining theoretical investigation, algorithm development, experimental evaluation and application-oriented validation. The major methodological dimensions include:

        1. Algorithm Design and Development: Formulating new computational algorithms and learning strategies to address limitations in existing methodologies.
        2. Mathematical and Statistical Modelling: Applying mathematical foundations, probability theory and statistical inference to understand and optimize learning behaviour.
        3. Knowledge Representation and Reasoning: Developing structured representations that facilitate automated knowledge acquisition and intelligent decision-making.
        4. Optimization Techniques: Employing computational optimization strategies to improve model performance, convergence and resource utilization.
        5. Experimental Analysis: Conducting systematic experiments using benchmark datasets and application-specific data to evaluate proposed approaches.
        6. Comparative Performance Evaluation: Assessing developed models against established approaches using appropriate performance metrics and statistical analysis.
        7. Generalization and Robustness Assessment: Investigating model behaviour under noisy, incomplete, imbalanced and previously unseen data conditions.
        8. Practical Implementation: Translating theoretical developments into functional computational frameworks and intelligent applications.

        Application-Oriented Research

        An important objective of my research is to translate computational advancements into practical solutions. I am interested in applying intelligent learning methodologies across domains where automated analysis and reliable decision-making can provide significant value.

        Potential application domains include:

        • Healthcare analytics and intelligent diagnostic support.
        • Digital media authentication and deepfake identification.
        • Natural language understanding and automated document analysis.
        • Financial analytics and intelligent risk assessment.
        • Cybersecurity and intelligent threat detection.
        • Smart cities and intelligent infrastructure.
        • Predictive analytics and industrial decision support.
        • Educational data mining and intelligent learning systems.
        • Knowledge discovery from large-scale scientific datasets.
        • Automated information retrieval and decision support systems.

        Research Vision and Future Directions

        My long-term research vision is to contribute towards the development of the next generation of intelligent systems that integrate learning, reasoning, knowledge discovery and autonomous decision-making. I aim to investigate computational models that can learn efficiently from limited and heterogeneous data, incorporate domain knowledge, adapt to dynamic environments and provide transparent explanations for their decisions.

        I am particularly interested in exploring the convergence of traditional Artificial Intelligence methodologies with modern developments in Deep Learning, Generative AI, Large Language Models and Multimodal Intelligence. The integration of symbolic and subsymbolic approaches offers promising opportunities for developing intelligent systems that combine the learning capabilities of neural models with the reasoning and interpretability of knowledge-based systems.

        Future research directions will also focus on resource-efficient artificial intelligence, trustworthy machine learning, automated knowledge representation and scalable intelligent computing. An important objective is to develop AI systems that are not only technologically advanced but also reliable, explainable, computationally sustainable and suitable for deployment in real-world environments.

        Ultimately, my research seeks to bridge the gap between theoretical advancements in computational intelligence and their practical realization. Through algorithmic innovation, interdisciplinary collaboration and application-driven research, I aim to contribute to the development of intelligent technologies that can enhance knowledge discovery, automate complex processes and support responsible decision-making in society.