Citation :

Shraddha Rai, Kontham Shiva Balaji, Patnam Pavan Kumar, S Sowjanya, 2026. "SevaSetu-ShantamCare: AI-Driven Ecosystem for Privacy Preserving Caregiving " ESP International Journal of Advancements in Science & Technology (ESP-IJAST)  Volume 4, Issue 2: 48-56.

Abstract :

India’s rapidly aging population, expected to surpass 340 million by 2050, faces significant challenges in providing dependable and reasonably priced elder care, particularly in rural and semi-urban areas with inadequate infrastructure and caregiver shortages. This paper proposes SevaSetu-ShantamCare, a decentralized, AI-powered ecosystem designed to deliver community-based and privacy-preserving elder care services. The platform integrates Hyperledger Fabric blockchain with Zero-Knowledge Proofs (zk-SNARKs) to ensure secure and confidential data handling. An intelligent caregiver–careseeker matching mechanism is implemented using a Multi-Agent Deep Reinforcement Learning (MADRL) framework combined with the Gale–Shapley stable matching algorithm for efficient service allocation. Additionally, an edge-assisted vernacular microlearning module provides rural women with localized training and blockchain-verified skill certificates, promoting economic empowerment. SOS safety mechanisms and smart-contract-based escrow payments further enhance trust and accountability within the ecosystem. Simulation results demonstrate improved matching efficiency and reduced latency compared to conventional elder care coordination systems, highlighting the platform’s potential to strengthen decentralized elder care services while supporting rural women’s participation in the caregiving workforce.

References :

[1] Shatam Care Foundation, “Redefining Elder Care through Technology and Inclusion,” ShatamCare Official Website, 2023.

[2] L. Huang, K. Gupta, and D. Singh, “Emergency response and SOS alert systems in home-based care applications,” in Proc. IEEE Int. Conf. Health Informatics, 2020, pp. 201–208.

[3] S. O. Mohammadi and A. Kalhor, “Privacy-preserving health data management: Architecture and challenges,” in Proc. IEEE Int. Conf. Trust, Privacy and Security in Intelligent Systems and Applications, 2017, pp. 45–52.

[4] R. Sharma and M. Patel, “Digital skill development through offline-accessible learning modules for rural caregivers,” J. Rural Dev., vol. 38, no. 2, pp. 98–115, 2019.

[5] M. Johansen and E. Leroy, “Socio-economic impacts of digital caregiver platforms in emerging economies,” Int. J. Social Economics, vol. 48, no. 9, pp. 1234–1250, 2021.

[6] P. Martínez-García, S. Nguyen, and T. Zhang, “User behaviour and privacy concerns in telecare platforms for the elderly,” J. Med. Syst., vol. 42, no. 7, 2018.

[7] United Nations Department of Economic and Social Affairs, “World Population Ageing 2023: Highlights,” UN, New York, 2023.

[8] Ministry of Statistics and Programme Implementation, “Elderly in India 2021,” Government of India, New Delhi, 2021.

[9] H. Ocheja, B. Flanagan, H. Ueda, and H. Ogata, “Managing lifelong learning records through blockchain,” Res. Pract. Technol. Enhanc. Learn., vol. 14, no. 1, p. 4, 2019.

[10] D. J. Bernstein et al., “BBS Signature Scheme,” W3C Draft Community Group Report, Decentralized Identity Foundation, 2023.

[11] J. Schulman, P. Moritz, S. Levine, M. Jordan, and P. Abbeel, “High-dimensional continuous control using generalised advantage estimation,” in Proc. ICLR, 2016.

[12] A. T. Corbett and J. R. Anderson, “Knowledge tracing: Modeling the acquisition of procedural knowledge,” User Model. User Adapted Interact., vol. 4, no. 4, pp. 253–278, 1994.

[13] J. Groth, “On the Size of Pairing-Based Non-Interactive Arguments,” in Proc. EUROCRYPT, 2016, pp. 305–326.

Keywords :

Decentralized Identity (DID), Zero-Knowledge Proofs (zk-SNARKs), Hyperledger Fabric, Multi-Agent Deep Reinforcement Learning, Gale-Shapley Algorithm, Edge Computing, Vernacular Microlearning, NFT Certification, Smart Contract Escrow, Progressive Web App, Elder Care, Rural Women Empowerment.