Artificial Intelligence, Computer Engineering, Multidisciplinary, Renewable Energy, Sustainability and the Environment
6
Scopus Publications
37
Scholar Citations
4
Scholar h-index
1
Scholar i10-index
Scopus Publications
A Hierarchical CNN Model for Brain Tumor Classification and Survival Rate Shivam Agarwal, Yogesh Kumar Gupta International Journal of Drug Delivery Technology, 2026 Automatic brain tumor segmentation and classification of MRIs are very important for diagnosing and treating brain tumors. Early and accurate detection greatly increases the chances of getting medical help on time, which in turn raises the chances of survival for patients. The dependability of these detection systems has a direct effect on how well doctors can make diagnoses and come up with effective treatment plans. Glioblastoma is among the most aggressive and lethal brain tumors; therefore, perfect accuracy in diagnosis and prognosis is essential to improving patient outcomes. This paper presents a Hierarchical Convolutional Neural Network (HCNN) model that utilizes relevant clinical data and tumor severity analysis to predict the overall survival of glioblastoma patients. The HCNN is a complex deep learning structure that combines structured rate of patient data with medical imaging to make tumor classification and survival prediction better. The model enhances MRI image feature extraction through transfer learning, thereby augmenting diagnostic accuracy and efficiency. The HCNN uses the image analysis capabilities of convolutional neural networks along with clinical records to quickly assess how a tumor is growing and how it will affect a patient's prognosis. The model works well, with a prediction accuracy of 99.67%. This shows that it could be a useful tool for making clinical decisions and planning personalized treatment. Fuzzy neural networks (FNNs) are often used to deal with unclear medical data, but they aren't very accurate, which makes them less useful in real-time clinical settings. So, the proposed HCNN architecture is a better and more reliable way to diagnose medical problems.
CFD: A Browser-Based Tool for Real-Time Carbon Emission Awareness Shivam Agarwal, Shubh Arora, Tanvi Sharma, Imran Khan 2026 2nd International Conference on Cognitive Computing in Engineering Communications Sciences and Biomedical Health Informatics Ic3ecsbhi 2026, 2026 Climate change is now a normal part of life, so it's important to keep track of and limit your carbon footprint. Every moment we spend in our environment generates carbon in different forms. We generate carbon emissions through activities such as breathing, moving, using electronic devices, and accessing the internet. This paper primarily focuses on the carbon emissions resulting from internet usage. This paper introduces the Carbon Footprint Detector (CFD), a Chrome extension for browsers that uses real-time data analytics to measure the carbon emissions caused by using the internet. The system uses the Chrome API to collect data on network transmissions, uses real-world conversion factors, and gives users session-based metrics like energy use (kWh), carbon emissions (grams <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{CO}_{2}$</tex>), and total environmental impact. The result of the experiment shows that <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{20}-\mathbf{300} \text{gms}$</tex> of CO2 is produced by the use of the internet, depending upon the use. The CFD tool has a capability to capture data with 98.5% accuracy and track all the emissions of CO2 by the different activities done by the user, and your current session summary while online. The system was designed to increase people's awareness of environmental issues, which may encourage them to support sustainability policies.
Edge-EmoNet: A Low-Latency Edge-based Deep Learning Framework for Real-Time Emotion Recognition with Attention-Optimized Feature Fusion L.M.I.Leo Joseph, Reema Rallan, Shivam Agarwal, Shiv Shakti Shrivastava, Gopinath D, A Periya Nayaki Proceedings of the 7th International Conference on Innovative Data Communication Technologies and Application Icidca 2025, 2025 Real-time facial emotion recognition (FER) in edge computing environments poses significant challenges due to the trade-off between accuracy, latency, and resource constraints. This paper presents Edge-EmoNet, a low-latency edge-based deep learning framework integrating a lightweight CNN–Transformer hybrid architecture with a novel Attention-Optimized Feature Fusion (AOFF) module. The proposed model is designed to efficiently capture both local and global facial features, while prioritizing emotion-relevant regions through spatial, channel, and multi-head attention mechanisms. Depthwise separable convolutions and quantization-aware training significantly reduce computational complexity and model size, enabling deployment on devices such as the NVIDIA Jetson Nano, Raspberry Pi 4, and Google Coral TPU. Experiments were conducted on the AffectNet dataset augmented with edge-device-captured samples. The proposed framework achieved a peak accuracy of 94.8%, outperforming MobileNetV3-Large (91.2%), EfficientNet-Lite0 (90.8%), and ShuffleNetV2 (89.9%). Inference latency was reduced to 28.4 ms/frame on the Jetson Nano, with a compact model size of 8.2 MB and energy consumption as low as 2.7W on Coral TPU. The model demonstrated consistent performance under varying lighting conditions, partial occlusion, and compression artifacts, confirming its robustness for real-world scenarios. These results establish Edge-EmoNet as a viable FER solution for embedded and portable systems where computational and energy resources are limited. The attention-driven fusion design not only enhances classification accuracy but also ensures that inference remains within real-time constraints, making it highly suitable for applications in human–computer interaction, assistive technologies, surveillance, and emotion-aware IoT systems.
A Comprehensive Evaluation of Secured Electronic Voting System Design based on Face Biometric Authentication Policy Pandarinath Potluri, R Jayakarthik, Shivam Agarwal, Shobana S, Venkata Padmavathi S, Aarthi R 8th International Conference on I Smac Iot in Social Mobile Analytics and Cloud I Smac 2024 Proceedings, 2024 In the field of electronic voting systems, ensuring secure and reliable authentication mechanisms is paramount to safeguarding the integrity and fairness of the democratic process. Face biometric authentication has emerged as a promising approach, integrating advanced deep learning algorithms for accurate and efficient verification of voters based on their facial features. This paper presents a comprehensive overview of the system architecture and design considerations for integrating face biometric authentication into electronic voting systems. It describes the hardware and software components essential for system functionality, discusses the selection of appropriate technologies for face recognition and encryption, and elaborates on the design of user interfaces, database structures, and ballot generation systems. Furthermore, the paper delves into the implementation of face detection and recognition algorithms, emphasizing the importance of anti-spoofing measures and multi-factor authentication mechanisms to enhance security. It also addresses voter registration processes, ballot generation, the voting process, and vote counting and verification procedures within the context of face biometric authentication. Additionally, the paper highlights the significance of robust security measures, including encryption techniques, access controls, and regular security audits, to mitigate cyber threats and ensure the integrity of the electoral process. By integrating face biometric authentication into electronic voting systems, this paper aims to contribute to the development of secure, transparent, and inclusive electoral systems, fostering trust and confidence in democratic governance, with an accuracy rate of 96%.
Big Data Privacy Issues Solutions Shivam Agarwal, Meghna Gupta, Ashish Sharma Proceedings of the IEEE International Conference Image Information Processing, 2019 As we all know that the 21 century is the century of Big Data. This data is the raw material for the production of immense social and economic values. This leads to a massive increase in data storage and data mining. The increasing number of people, sensors, and devices are the main causes of big data. This data creates great value for the innovation, productivity, efficiency, and growth of the global economy. But at the same time this data generates a “data deluge” which generates privacy concerns; as a result, it creates a backlash dampening the economy of the data and the innovation. So to maintain the privacy of individuals and the production of the data we need to create some advanced policies which can effectively work on big data because the policies or algorithms which we have are not so much advanced that they can deal with that much amount of data on the timely basis. This paper presents the privacy issues which come across dealing with big data and suggests a few ways to protect the data-intensive information systems.
CFD: A Browser-Based Tool for Real-Time Carbon Emission Awareness S Agarwal, S Arora, T Sharma, I Khan 2026 2nd International Conference on Cognitive Computing in Engineering … , 2026 2026
Edge-EmoNet: A Low-Latency Edge-based Deep Learning Framework for Real-Time Emotion Recognition with Attention-Optimized Feature Fusion LMIL Joseph, R Rallan, S Agarwal, SS Shrivastava, AP Nayaki 2025 7th International Conference on Innovative Data Communication … , 2025 2025
A Comprehensive Evaluation of Secured Electronic Voting System Design based on Face Biometric Authentication Policy P Potluri, R Jayakarthik, S Agarwal 2024 8th International Conference on I-SMAC (IoT in Social, Mobile … , 2024 2024 Citations: 1
Melanoma Classification Using Deep Learning A Tripathi, R Singh, R Singh, A Bansal, A Kumar, S Agarwal Journal of Electrical Systems 20 (3), 2677-2691 , 2024 2024
S++: A fast and deployable secure-computation framework for privacy-preserving neural network training P Ramachandran, S Agarwal, A Mondal, A Shah, D Gupta arXiv preprint arXiv:2101.12078 , 2021 2021 Citations: 12
Big Data Privacy Issues & Solutions S Agarwal, M Gupta, A Sharma 2019 Fifth International Conference on Image Information Processing (ICIIP … , 2019 2019 Citations: 6
Barriers and Success factors of Women Entrepreneurship in India. S Arora, S Agarwal Global Journal of Enterprise Information System 10 (3) , 2019 2019 Citations: 7
An enhanced method for privacy S Agarwal, S Sachdeva Preserving Data Publishing. Studies in Computational Intelligence 713, 61-75 , 2018 2018 Citations: 9
An Efficient Method for Maintaining Privacy in Published Data A Shivam, A Sharma, M Agarwal Vivekananda Journal of Research 7 (1) , 2018 2018
An Enhanced Method for Privacy-Preserving Data Publishing S Agarwal, S Sachdeva Innovations in Computational Intelligence: Best Selected Papers of the Third … , 2017 2017 Citations: 2
MOST CITED SCHOLAR PUBLICATIONS
S++: A fast and deployable secure-computation framework for privacy-preserving neural network training P Ramachandran, S Agarwal, A Mondal, A Shah, D Gupta arXiv preprint arXiv:2101.12078 , 2021 2021 Citations: 12
An enhanced method for privacy S Agarwal, S Sachdeva Preserving Data Publishing. Studies in Computational Intelligence 713, 61-75 , 2018 2018 Citations: 9
Barriers and Success factors of Women Entrepreneurship in India. S Arora, S Agarwal Global Journal of Enterprise Information System 10 (3) , 2019 2019 Citations: 7
Big Data Privacy Issues & Solutions S Agarwal, M Gupta, A Sharma 2019 Fifth International Conference on Image Information Processing (ICIIP … , 2019 2019 Citations: 6
An Enhanced Method for Privacy-Preserving Data Publishing S Agarwal, S Sachdeva Innovations in Computational Intelligence: Best Selected Papers of the Third … , 2017 2017 Citations: 2
A Comprehensive Evaluation of Secured Electronic Voting System Design based on Face Biometric Authentication Policy P Potluri, R Jayakarthik, S Agarwal 2024 8th International Conference on I-SMAC (IoT in Social, Mobile … , 2024 2024 Citations: 1
CFD: A Browser-Based Tool for Real-Time Carbon Emission Awareness S Agarwal, S Arora, T Sharma, I Khan 2026 2nd International Conference on Cognitive Computing in Engineering … , 2026 2026
Edge-EmoNet: A Low-Latency Edge-based Deep Learning Framework for Real-Time Emotion Recognition with Attention-Optimized Feature Fusion LMIL Joseph, R Rallan, S Agarwal, SS Shrivastava, AP Nayaki 2025 7th International Conference on Innovative Data Communication … , 2025 2025
Melanoma Classification Using Deep Learning A Tripathi, R Singh, R Singh, A Bansal, A Kumar, S Agarwal Journal of Electrical Systems 20 (3), 2677-2691 , 2024 2024
An Efficient Method for Maintaining Privacy in Published Data A Shivam, A Sharma, M Agarwal Vivekananda Journal of Research 7 (1) , 2018 2018
