SAShubhani Aggarwal

Shubhani Aggarwal

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Shubhani Aggarwal has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Explainable soft-voting classifier for heart disease prediction using SHAP and LIME

    by Samiksha Walia, Samdisha Walia, Aanshi Bhardwaj, Shruti Arora, Shubhani Aggarwal, Parveen Siwach

    Heart disease remains a major global health challenge, underscoring the need for predictive models that are both accurate and interpretable to support early diagnosis and clinical decision-making. Using Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) in this study allowed for a deeper level of understanding of model predictions as well as provided viable alternative ways to overcome the challenges associated with black-box classifiers. Using a soft-voting ensemble technique that combined representations for Random Forest (RF), Decision Tree (DT), and Support Vector Machines (SVM) was applied to evaluate a publicly available heart disease dataset, containing 5110 records with each record containing 76 attributes. A total of 14 clinically relevant features were identified and evaluated using an 80/20 train-test split for the experimental setup, with results further validated by 5-fold cross-validation. The proposed soft-voting ensemble model achieved an accuracy of 89.10%, precision of 83.90%, recall of 95.20%, and F1-score of 89.90%, out-performing all individual baseline models and many of the recent XAI-enhanced deep learning models. The combination of SHAP and LIME allowed for both global and local interpretations of the model’s outputs, providing interpretable insights as to features like cp, thal, ca, and oldpeak contributed to the predictions and aligning these features with known cardiovascular risk factors. The results of this research demonstrate how interpretable (or explainable) ensemble-learning mechanisms can confer highly reliable, clinically useful heart disease risk predictions.


  • Secure and Decentralized Heart Sound Analysis using Federated Learning and Blockchain Technology

    by Shivani Agarwal, Meenakshi Kandpal, Vishan Kumar Gupta, Shubhani Aggarwal, Paras Jain

    Early diagnosis of cardiac abnormalities depends on accurate classification of heart sounds, but centralized training methods run the danger of violating patient privacy. We thus propose a privacy-preserving and reliable heart sound abnormality detection system combining Blockchain Technology with Federated Learning (FL). Training is spread among seven clients, each simulating an independent data source, using a preprocessed dataset from the PhysioNet Challenge 2016 to enable distributed learning without sharing raw data. CNN-LSTM model using FedAvg achieved the best performance: 94\% accuracy, 0.90 precision, 0.96 recall, and an AUC of 0.98 among five deep learning architectures evaluated with FedAvg and FedProx strategies. Along with metadata including client ID and round number, SHA-256 hashes of local and global model weights were recorded on a local Ethereum blockchain following every communication round to guarantee model integrity. The hash of the final model is revalidated against the blockchain to confirm authenticity prior to deployment. It then guarantees safe, distributed, clinically valuable AI-based diagnostics by real-time classification of heart sounds as normal or abnormal.


  • Quantum Computing Essentials: Bridging Theory and Practice for New Learners

    by Vansh Aggarwal, Shubhani Aggarwal, Aanshi Bhardwaj, Vishan Kumar Gupta

    This paper investigates the core principles of quantum computation, providing an in-depth understanding of quantum phenomena and illustrating how these principles form the scientific foundation of the field. The pivotal physical concepts, such as properties of subatomic particles, including electrons and photons, as well as their mathematical description through linear algebra are examined. It focuses on the qubit, the quantum analogue of a classical bit, featuring properties like superposition, entanglement, and wave function collapse, which redefine the traditional concept of information processing. The mathematical structures that underlie quantum system modelling—vector spaces, tensor products, and Dirac notation—are also systematically explained. Essential components of quantum computation involve logic gates such as Pauli matrices and Hadamard gates, which demonstrate the novel application of qubits in unique ways. This sets up an important theme of the interdependence and potential for transformation of quantum states through the illustration of advanced ideas of quantum entanglement and teleportation. It makes an outstanding example of how quantum circuits exploit reversibility and superposition to solve complex problems at unprecedented levels of efficiency. The paper also highlights the Deutsch-Jozsa algorithm as a compelling example of quantum superiority over traditional computational approaches. Together, these findings emphasize the transformative potential of quantum computing for science and industry.


  • Integrating Artificial Intelligence and Machine Learning in Autism Detection via Gut Microbiome Analysis

    by Shobhita Singh, Shubhani Aggarwal, Aishani Singh, Anupriya Sharma

    The Autism Spectrum Disorder (ASD) diagnosis and detection in its initial stages is a more complex issue in the face of the wide-ranging, diverse nature and causes. Subsequent literature inclined towards a possible correlation of gut microbiome with ASD, and its disclosure presents a more promising attribute for imminent discovery conduits. The dataset on gut microbiome associated with ASD focuses specifically on the microbial compositions obtained through 16S rRNA sequencing. This study presents a novel method that integrates Artificial Intelligence employing various Machine Learning (ML) robust classifiers such that Support Vector Machines (SVM), Random Forest, k-Nearest Neighbors (KNN), Logistic Regression, and Artificial Neural Networks (ANN), additionally PCA and k-means clustering is implemented for feature extraction to reveal important hidden patterns of ASD associated microbiomes from microbiome profiles. By integrating these model classifiers, the ensemble technique was developed to harness the strengths of each model, which enhances the dependability of the gut microbiome and offers a novel approach. The ensemble method suggested has an accuracy of 98.75%, a precision of 95.11%, a recall of 96.47% and an F1 score of 98.28% in the early determination of autism. The observational feature of this multifaceted approach not only enhances accuracy and precision but also provides a more complete picture of the role of autism spectrum disorders and eventually leads to the development of interventions and personalised approaches to these problems.


  • Neuro-Inspired Alert System for Air Quality Prediction Using Ensemble Preprocessing and SNN Classification

    by Sneh Sharma, Kashish Devgan, Devanshi Jangra, Aanshi Bhardwaj, Shubhani Aggarwal

    Air pollution has emerged as a critical challenge, directly affecting human health, urban sustainability, and climate systems. Traditional air-quality index (AQI) prediction models often struggle to provide timely alerts because they are not very sensitive to changes over time and are hard to understand. This paper proposes a Neuro-Inspired Alert System for Air Quality Prediction (NAS--AQP) that incorporates an ensemble learning approach using voting regression to enhance input quality, followed by classification through a Spiking Neural Network (SNN). The system is designed such that it captures the temporal and nonlinear relationships between air pollutants such as Nitrogen Dioxide ($NO_2$), Sulphur Dioxide ($SO_2$), Respirable Suspended Particulate Matter (RSPM) and Suspended Particulate Matter (SPM). The proposed method starts with preprocessing of the data and normalizing the features. After that, models like Linear Regression (LR), Random Forest (RF), and Decision Tree (DT) are trained and evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination ($R^2$) metrics. After the training of above models, a voting based ensemble approach is used to improve AQI regression accuracy. A threshold based rule is then used to convert received, AQI predictions into binary alerts. Finally, SNN is trained to classify these alerts to achieve energy, efficient, real time, alerting by using its temporal coding and sparse activation. The ensemble voting regression model achieved an RMSE of 8.43 and MAE of 6.21, while the SNN classifier attained a classification accuracy of 92.4%.


  • Blockchain-Based Content Retrieval Mechanism in NDN-Enabled V2G Networks

    by Shubhani Aggarwal, Neeraj Kumar, Nazeeruddin Mohammad, Ahmed Barnawi

    In the coming years, massive amounts of data are likely to be traded in vehicle-to-grid (V2G) networks to enhance traffic efficiency and safety through vehicular communications. However, several challenges need to be addressed before realizing the full potential of V2G networks. These challenges include the privacy-preservation of users, secure caching, scalability in deep environments, unreliability in high mobility events, and low efficiency in large networks. To overcome these challenges in V2G networks, named data networking (NDN) offers a good solution. It provides a new future Internet architecture: “named content-based” rather than “host addresses.” The main focus of NDN in V2G networks is to provide data availability, network performance, data retrieval, and data distribution. However, the presence of NDN in V2G networks introduces several issues like privacy and trust among vehicular nodes. Hence, this article proposes a system model based on blockchain technology in NDN-enabled V2G networks. This model provides secure and fast named content searching and enhances the trust among vehicular nodes. The simulation results show that the block propagation latency of NDN-based blockchain is less than the IP-based blockchain systems. In addition, the performance of the proposed scheme outperforms an existing scheme. The reason is to use the proof-of-authority consensus mechanism compared to proof of work, which uses high mining computation power. Furthermore, the proposed scheme increases the trust and transparency in NDN-enabled V2G networks.


  • Authentication of Smart Grid by Integrating QKD and Blockchain in SCADA Systems

    by Shubhani Aggarwal, Georges Kaddoum

    Information and Communication Technology (ICT) provides customers with utilities and smart grid solutions, enabling enhanced monitoring and control of energy management systems. This technology is poised to elevate the reliability, sustainability, and efficiency of future electric grids through the implementation of advanced metering infrastructure (AMI). However, current Supervisory Control and Data Acquisition (SCADA) systems lack trusted machine authentication in smart grid communications, leaving the electric grid vulnerable to cyberattacks via sophisticated network technologies such as wireless access points, sensors, routers, and gateways. Therefore, ensuring proper management of data integrity from field sensors is crucial to enhance the reliability of SCADA systems. In this context, the utilization of quantum key distribution (QKD) key pairs is proposed to uphold integrity in smart grid communications. This paper presents a fibre optic blockchain network designed to manage and utilize cryptographic keys, facilitating the authentication of peer-to-peer (P2P) communications in SCADA systems. This demonstration underscores the feasibility of employing QKD and blockchain to further strengthen the integrity and authentication of smart grid communications. Additionally, this paper delves into discussing the performance metrics and overhead expenses of the proposed scheme in comparison with existing state-of-the-art proposals. Simulation results highlight the significant impact of blockchain size on the system setups throughput and latency.


  • Load Balancing and Clustering Scheme for Real-Time VoIP Applications

    by Shubhani Aggarwal, Nitish Mahajan, Sakshi Kaushal, Harish Kumar


  • On a Hardware Selection Model for Analysis of VoIP-Based Real-Time Applications

    by Shubhani Aggarwal, Gurjot Kaur, Jasleen Kaur, Nitish Mahajan, Naresh Kumar, Makhan Singh