Shadab Hussain

Shadab Hussain

Auto-generated profile, based on publicly available information

Shadab Hussain

MathCo, Chicago, USA

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
1 December 2021
Verified
Conference Paper
Closed access
SHShadab Hussain
Shadab Hussain
SNSantosh Kumar Nanda
Santosh Kumar Nanda
SBSusmith Barigidad
Susmith Barigidad
SAShadab Akhtar
Shadab Akhtar
SUSuaib
Suaib
NRNiranjan Kumar Ray
Niranjan Kumar Ray
In the last few years, with increased population the most critical component of human life is healthcare. Compare to other deadly diseases, heart disease is one of the most lethal diseases, affecting the lives of millions of people worldwide. It is very important to detect heart disease must early so the loss of lives can be prevented. The availability of enormous amounts of data for medical diagnostics has aided in the development of complex learning-based models for automated early detection of cardiac problems. The classical machine learning approaches unable to generalize the new data sets which have not been seen in the training set. Therefore, the trained model has less accuracy in prediction stage. To minimize this issue, need to balance between training and testing datasets. This paper proposes a novel deep learning architecture using a 1D convolutional neural network for classification between healthy and non-healthy persons with balanced datasets to reduce the limitations of classical machine learning approach. Several clinical parameters are used for evaluating the risk contour in the patients which supports in early diagnosis. Various regularization methods are used to avoid overfitting in the proposed model. The proposed model achieves over 97% training accuracy and 96% test accuracy on the dataset. This is compared in detail with other machine learning algorithms using various performance parameters which proves the effectiveness of the proposed model.

24 March 2026 in IEEE Access
Verified
Journal Article
Open access
ASAlok Kumar Srivastava
Alok Kumar Srivastava
SHShadab Hussain
Shadab Hussain
SSShiru Sharma
Shiru Sharma
AVAshish Verma
Ashish Verma
NSNeeraj Sharma
Neeraj Sharma
Multiclass brain tumor classification from magnetic resonance imaging (MRI) remains challenging due to subtle inter-class visual similarities, particularly for anatomically small and heterogeneous tumor types such as pituitary lesions. To address these challenges, this paper presents a hybrid classical-quantum learning framework that integrates a deep convolutional feature extractor from the ResNet family with a variational quantum neural network (QNN) head for enhanced feature representation. In the present work, classical deep features extracted by the ResNet model are encoded into a six-qubit quantum circuit, enabling richer feature interactions within a high-dimensional Hilbert space. In addition, an anatomically guided Kernel-based Center Cropping (KCC) strategy is introduced as a deterministic spatial prior to emphasize anatomically relevant central brain structures, particularly benefiting challenging pituitary tumor cases. The proposed Kernel-based Center Cropping–Hybrid Quantum Neural Network (KCC-HQNN) framework is trained and evaluated on a publicly available composite four-class brain MRI dataset curated from Kaggle sources, comprising glioma, meningioma, pituitary tumor, and no-tumor categories. Experimental results across multiple ResNet variants demonstrate that the hybrid quantum–classical models consistently outperform their purely classical counterparts, achieving classification accuracy of up to 99%, while macro-averaged precision, recall, and F1 scores consistently fall in the range of approximately 0.95–0.99 across different ResNet variants. Reliability and reproducibility are further validated through stratified five-fold cross-validation and repeated experiments using multiple random initialization seeds, yielding a mean classification accuracy of 99.00 ± 0.08%, macro F1-score of 0.986 ± 0.11, and weighted F1-score of 0.989 ± 0.12, while cross-dataset evaluation on independent IEEE DataPort MRI datasets demonstrates robust generalization under dataset shift. All experiments are conducted on publicly available retrospective datasets using a quantum simulator. These results indicate that combining quantum feature processing with anatomically informed spatial processing improves multiclass discrimination of brain tumors.

30 May 2025
Verified
Book Chapter
Closed access
RSRam Krishna Sharma
Ram Krishna Sharma
TSTilak Saxena
Tilak Saxena
SKSandeep Kanaujia
Sandeep Kanaujia
SHShadab Hussain
Shadab Hussain
The integration of non-fossil fuel-based vehicles with non-conventional renewable energy, is necessary in the field of sustainable energy usage. This review paper explains how non-conventional energy sources are related to the Electric Vehicles. This paper also reviews advantages, problems and their solutions and prominent technologies. There are two terms: Non-conventional Energy is a clean energy however in reducing emission of greenhouse gases, EVs are the perfect solutions. By combining these two, a new system with less dependency on petroleum-based fuels and stable grids can be developed. In this paper we reviewed, different techniques of integrating EVs with non-conventional energy, V2G technology, smart grid, and energy storage system along with new trends, problems, solutions and future scopes. As demand of EV technology increases, it requires a fast fuel-efficient charging which can carry demands of high power and integration of non-conventional energy with extremely-fast EV charging systems by the use of MPCs, which can manage and distribute energy between locations.

30 June 2026
Verified
Book Chapter
Closed access
SBSusmith Rajendra Barigidad
Susmith Rajendra Barigidad
SHShadab Hussain
Shadab Hussain
PGPranav Gupta
Pranav Gupta
ZAZia Akbar
Zia Akbar
SGSandeep Gupta
Sandeep Gupta
SKSandeep Kanaujia
Sandeep Kanaujia
Machine learning methods offer versatile approaches for energy consumption forecasting, system efficiency improvement and smart grid management. In this study, we explore different ML models for the predictive energy optimisation such as linear regression, support vector machines, random trees and random forests, artificial neural networks, and long short-term memory networks. A systematic review of literature is carried out to review the traditional and modern methods. We experiment with real datasets to train and evaluate models where the performance measures are RMSE, MAE, and accuracy should be achieved. The findings show the effectiveness of deep learning models including LSTM networks in modeling temporal dependencies of energy consumption. The paper also addresses shortcomings like data quality, model interpretability, and scalability. Finally, future directions of research are proposed to enhance the predictive capabilities and integration with renewable energy sources.

9 January 2026
Verified
Book Chapter
Closed access
SSSatya Prakash Singh
Satya Prakash Singh
PSPrabhat Chandra Shrivastava
Prabhat Chandra Shrivastava
PKPrashant Kumar
Prashant Kumar
MTManish Tiwari
Manish Tiwari
SHShadab Hussain
Shadab Hussain
Antenna systems having small size, higher efficiency and stable radiation behaviour at terahertz frequencies are need for today's scenario for sustainable energy communication network. Proposed work suggests the design and optimization of DRA antenna for THz microwave frequency which is based on the parameters like voltage standing wave ratio (VSWR), axial ratio, and total efficiency. The optimized DRA possesses a value of VSWR that is less than 2.0 at the entire operating frequency that makes it an ideal match of the impedance. The antenna axial ratio is approximately 1.2 dB, which ensures the stability of circular polarization, suitable to the capacity of wireless connections of high capacity. Moreover, the design will achieve a maximum overall efficiency of about 85, which is very optimum in the context of energy conscious and low loss communication systems. Because of these features, the proposed THz DRA can be applied in smart grid successfully. Sustainable wireless, IoT devices which are energy-efficient and communication.

11 July 2025
Verified
Book Chapter
Closed access
PTPradeep Kumar Tiwari
Pradeep Kumar Tiwari
SDSantosh Dubey
Santosh Dubey
RSRavi Srivastava
Ravi Srivastava
SSSatya Prakash Singh
Satya Prakash Singh
SKSandeep Kanaujia
Sandeep Kanaujia
SHShadab Hussain
Shadab Hussain
The speed of progress in wireless communication requires smart, adaptive antenna systems that can enhance network performance in dynamic environments. This chapter presents AI-based adaptive antenna systems for smart communication networks. By using machine learning algorithms, the antenna adjusts beamforming and polarization in real-time to optimize signal quality, decrease interference, and increase throughput. We describe the architecture, the algorithmic framework, and the experimental validation. The results show a remarkable improvement in spectral efficiency and network reliability, highlighting the superiority of AI in future adaptive antenna technology.