Browsing by Author "Moirangthem Biken Singh"

Now showing 1 - 4 of 4

COVID-19 Spread Detection and Controlling with Fog-based Infection Probability Evaluation Model
(Association for Computing Machinery, 2023) Moirangthem Biken Singh; Suraj Mahawar; Himanshu Singh; Ajay Pratap
COVID-19 has created a pandemic worldwide, paused the path of building the future, and is still ongoing without any long-term solution. The time taken in vaccine distribution is too slow compared to the spread of COVID-19. Hence, it is important to be aware and take precautions on time without delaying and waiting for long-duration after getting infected with the virus. Technology nowadays is more advanced than ever before. Almost everyone has access to at least one mobile device with internet connection. Therefore, we propose a Fog Server (FS) based system that helps create awareness about the spread of COVID-19 within the surroundings of an individual, utilizing the concept of Hidden Markov Model (HMM) and Bluetooth contact tracing in polynomial computational time complexity. Moreover, we evaluate the effectiveness of the proposed model through real-world data analysis on different simulation settings. © 2023 ACM.
Criticality and Utility-Aware Fog Computing System for Remote Health Monitoring
(Institute of Electrical and Electronics Engineers Inc., 2023) Moirangthem Biken Singh; Navneet Taunk; Naveen Kumar Mall; Ajay Pratap
Growing remote health system allows continuous monitoring of patients' conditions outside medical facilities. However, the real-time smart-healthcare applications having latency limitations, must be solved efficiently. Fog computing is emerging as an efficient solution for such real-time applications. Therefore, Medical Centers (MCs) are becoming more interested in offering IoT-based remote health monitoring services to get profited by deploying fog resources. However, an efficient algorithmic model for allocating limited fog computing resources in a criticality-aware smart-healthcare system while considering the profit of MCs is needed. Thus, we formulate an optimization problem by maximizing system utility, calculate as a linear combination of MC's profit and patients' cost together. We propose a flat-pricing based scheme to measure the profit of MC in health monitoring system. Further, we propose a swapping-based heuristic to maximize the system utility. The proposed heuristic is evaluated on various parameters and shown to be closed to the optimal while considering the criticality of patients and the profit of MC, together. Through extensive simulations, analysis on real-world data and prototype implementation, we find that the proposed heuristic achieves an average utility of 94.5% of the optimal, in polynomial time complexity. © 2008-2012 IEEE.
Energy-Efficient and Privacy-Preserving Blockchain Based Federated Learning for Smart Healthcare System
(Institute of Electrical and Electronics Engineers Inc., 2024) Moirangthem Biken Singh; Himanshu Singh; Ajay Pratap
The privacy-focused concept of Federated Learning (FL) allows local data processing without disclosing patients' health details to a central server. However, its vulnerability to privacy breaches through shared model weights and susceptibility to a single point of failure remain concerns. Energy constraints of Wireless Body Area Networks (WBANs) necessitate considering computation and transmission energy in the FL process. Thus, this article introduces a smart healthcare system prioritizing energy efficiency and privacy through a blockchain-backed FL model. Yet, WBAN users might be unwilling to share data without adequate incentives, and miners might hesitate due to the high energy usage associated with maintaining the blockchain. Therefore, an optimization problem is formulated to maximize system utility while considering energy, WBAN incentives, miner revenue, and FL loss. A computationally efficient stable matching-based algorithm is proposed for optimizing utility via associating WBANs and miners. Associated WBANs use Quantized Neural Networks (QNNs) to minimize computation energy. Moreover, this work integrates Differential Privacy (DP) and Homomorphic Encryption (HE) mechanisms to prevent information leakage by adding noise to gradients before updating model weights and encrypting consequences before transmitting them to miners. Real-world experiments validate the framework, yielding an average of 15.1%, 9.03%, and 15.35% improvements over existing methods. © 2008-2012 IEEE.
Optimized Doctor Recommendation System using Supervised Machine Learning
(Association for Computing Machinery, 2023) Himanshu Singh; Moirangthem Biken Singh; Ranju Sharma; Jayesh Gat; Ayush Kumar Agrawal; Ajay Pratap
In the past decade, we have seen many patients and healthcare problems. Due to this, patients find difficulty choosing doctors according to their disease. Several Machine Learning (ML) based techniques already exist to predict doctors based on patient's health conditions. However, it is essential to accurately recommend doctors to patients with low errors based on patients' health conditions. Therefore, we propose a method that assigns quantitative importance (weight) to each feature using an ML technique. Moreover, we offer a framework to recommend doctors based on the similarity score and doctor's skill score, which utilizes weight prediction to enhance operational efficiency. Additionally, on real-world datasets, the effectiveness of the proposed framework is demonstrated empirically by lowering the average loss by roughly 34% and 3% as compared to Convolutional Neural Network (CNN) and Support Vector Machine (SVM), respectively. The outcome demonstrates that the algorithm can efficiently recommend doctors to patients compared to state-of-the-art techniques. This analysis technique aid patients in opting for the right doctor. © 2023 ACM.