Blockchain-Enabled Secure and Interoperable Digital Twin Framework for Sustainable Industry 5.0 Smart Cities
ブロックチェーン対応の安全で相互運用可能なデジタルツインフレームワークによる持続可能なインダストリー5.0スマートシティ (AI 翻訳)
P. Janaki, Ramal E. Anbalagan
🤖 gxceed AI 要約
日本語
本論文は、インダストリー5.0スマートシティ向けに、ブロックチェーンとハイブリッド深層学習（GNN、LSTM、CNN）を統合したデジタルツインフレームワークを提案する。実験結果では、交通流予測96.4%、エネルギー需要予測93.7%の精度を達成し、遅延を37%削減。さらに、管理コスト25%削減、運用エネルギー消費21%削減、二酸化炭素排出量18%削減を実現し、持続可能性に貢献する。
English
This paper proposes a blockchain-enabled secure and interoperable digital twin framework for Industry 5.0 smart cities, integrating hybrid deep learning (GNN, LSTM, CNN) for real-time monitoring and optimization. Experimental results show 96.4% traffic flow prediction accuracy, 93.7% energy demand prediction accuracy, and 37% latency reduction. The framework achieves 25% management cost reduction, 21% operational energy reduction, and 18% carbon emission reduction, contributing to sustainable urban development.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本ではSociety 5.0の実現に向け、スマートシティとカーボンニュートラルの統合が進んでおり、本フレームワークはブロックチェーンによるデータセキュリティとAIによる最適化を通じて、日本の都市のGX（グリーントランスフォーメーション）に貢献できる可能性がある。
In the global GX context
Globally, this framework aligns with the UN SDGs and Industry 5.0 principles, offering a scalable approach to smart city sustainability. It addresses key challenges in data interoperability and energy optimization, making it relevant for cities pursuing carbon neutrality and digital transformation under TCFD and ISSB frameworks.
👥 読者別の含意
🔬研究者:Provides a novel integration of blockchain, digital twins, and deep learning for sustainable smart cities, with quantifiable performance metrics.
🏢実務担当者:Offers a practical framework for reducing operational costs and carbon emissions in urban infrastructure, with demonstrated efficiency gains.
🏛政策担当者:Demonstrates how blockchain and AI can support city-level sustainability targets and data integrity, relevant for smart city policy and GX planning.
📄 Abstract（原文）
Industry 5.0 also focuses on the human-machine collaboration, sustainability, and resilience in urban ecosystems, in which Digital Twin (DT) technology is crucial to ensure real-time monitoring, forecasting, and optimization. Interoperability, scalability, and data security are problematic to large-scale installations of smart cities. To implement smart cities based on Industry 5.0, this paper proposes a Blockchain-Enabled Secure and Interoperable Digital Twin Framework to ensure trusted, efficient, and sustainability in its operations. The framework involves the use of blockchain technology to provide interoperability between different urban subsystems in terms of cross-domain data sharing, tamper-proofed data sharing, and decentralized trust management. The system applies hybrid deep learning to help make advanced decisions: Graph Neural Networks (GNNs) in relational dependency optimization in energy and transportation grids, Long Short-Term Memory (LSTM) models in sequential traffic and energy demand prediction, and Convolutional Neural Networks (CNNs) in spatiotemporal feature extraction. An edge-cloud collaborative architecture ensures the scalable and low-latency provision of DTs in different smart city domains. The proposed framework, compared to traditional cloud-only DT systems, predicts traffic flows with 96.4% accuracy, energy demand with 93.7% and can reduce latency by 37 % based on experimental results, using simulated data of a smart city. Blockchain integration boosts data integrity by 99.2, reduces cybersecurity issues by 42 and speeds up cross-platform interoperability 28 times. Also, it enables the city-scale management cost reduction by 25 percent, operational energy consumption reduction by 21 percent, and carbon emission reduction by 18 percent, which is the purpose of safe, intelligent, and sustainable smart cities. The framework will form the foundation of the Industry 5.0 by addressing critical concerns in dependable data exchange, real-time predictive intelligence, and resource optimization that will be sustainable.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.1109/cicn70047.2026.11594263first seen 2026-07-13 07:15:57
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。