Nadia Dahmani, Imen Ben Salem, Syed Muhammad Salman Bukhari
Abstract Air quality (AQ) related health risks are increasing globally, creating urgent demand for artificial intelligence (AI) systems that are privacy-preserving, transparent, and auditable. Although Federated Learning (FL), Distributed Ledger Technologies (DLT), and Explainable AI (XAI) are widely recognized as core components of trustworthy AI, existing research remains divided across technical and application domains. This study conducts a computational, multistage systematic review (SR) of scholarly literature records published between 2011 and 2025 using the Semantic Scholar Graph API with intersection and union search strategies. A total of 13,458 records were retrieved and refined into a research-grade corpus of 7,215 publications through DOI-based deduplication, abstract quality diagnostics, venue and publication type screening, and exclusion of non-research artifacts. We used synergy detection, bibliometric analysis, and semantic clustering to study how these technologies are combined and distributed across research domains. The semantic clustering was performed using Sentence-BERT embeddings and UMAP. The results reveal a major structural gap. Among the 6,942 technology-tagged publications in the final 7,215-paper corpus, only 25 studies were identified as triple-synergy candidates that jointly mention or report the combined use of FL, DLT, and XAI, accounting for approximately 0.4%. Among these 25 triple-synergy publications, only two studies (8%) addressed climate or environmental applications, whereas 23 studies (92%) focused on healthcare or general AI. Semantic analysis further categorizes the studies into four areas: environmental sensing, provenance, governance, and clinical risk modeling. This division creates a critical challenge for scalable deployment, cross-domain interoperability, and policy-ready AI systems for AQ-health decision-making. To address this gap, we propose the Green-AI-Trust Stack, a layered architectural framework that integrates three complementary pillars (FL for privacy-preserving distributed learning, DLT for verifiable data and model provenance, and XAI for interpretable inference and decision support within a unified AQI-health pipeline). The findings provide practical direction for researchers, policymakers, and practitioners by identifying key research gaps, methodological needs, and future opportunities for reliable, auditable, and explainable AQI-health AI systems.
Air pollutants poses a widespread chance to human health and the environment, with diverse assets contributing to its escalation. University campuses, which function hubs for instructional and social sports, are not proof against this trouble. This observe aimed to develop a predictive model that estimates the proportion of air pollution as a consequence of smoking behavior amongst college students and school members within a college campus placing. The studies employed a complete methodology, combining a smoking habits survey, air quality tracking, and advanced predictive modeling strategies. The findings discovered that smoking conduct contributed to about 22.7% of the general air pollution degrees on campus. The predictive model, advanced the usage of a random forest algorithm, demonstrated strong overall performance, with an R-squared price of zero.88 and a root suggest squared mistakes of 0.052. The spatial analysis highlighted regions with better degrees of air pollution resulting from smoking, imparting precious statistics for focused interventions. The effects underscore the big effect of smoking on air excellent and the potential health risks related to publicity to smoking-related air pollutants. The observe gives quantitative evidence to inform focused interventions and regulations aimed toward reducing smoking-related air pollution on college campuses, ultimately selling a healthier campus surroundings. By quantifying the contribution of smoking habits to air pollution levels and identifying hotspots of subject, this studies contributes to the growing frame of knowledge on the environmental and health influences of smoking. The findings emphasize the importance of adopting a holistic approach that considers diverse contributing elements and fosters collaborative efforts amongst stakeholders to mitigate the unfavorable consequences of air pollutants.
Industrial carbon emissions play a major role in environmental pollution and climate change. Because of this, industries are required to continuously monitor their emissions and ensure they follow environmental regulations. Traditional emission monitoring systems generally rely on centralized databases, which can sometimes lead to problems such as delayed reporting, lack of transparency, and the possibility of data being altered. To overcome these issues, this paper introduces CarbonChain, a decentralized carbon emission monitoring system that combines Internet of Things (IoT) sensing technologies with blockchain verification. Environmental parameters such as gas concentration and particulate matter are collected in real time using sensors connected to microcontroller units. The sensor readings are then transmitted to a backend server where the data is validated and categorized. After validation, the emission records are stored on the blockchain through smart contracts, generating secure transaction hashes that ensure the integrity of the data. A web-based dashboard allows regulators and industry stakeholders to monitor emission levels, check compliance status, and verify blockchain records in real time. By combining IoT-based sensing with blockchain technology, CarbonChain creates a transparent and tamper-resistant monitoring platform that can support environmental auditing and carbon credit verification.
Gukanraj S, Jeeva Rekha R, Dharshan M, Mohan Murthy M · 7 authors
Environmental pollution poses a significant threat to public health and ecosystems, demanding advanced methods for real-time monitoring and source identification. Traditional IoT monitoring systems often fail to capture complex spatiotemporal patterns and raise privacy concerns. This paper introduces a robust, privacy-preserving IoT-based environmental monitoring framework integrating Times Net for temporal feature extraction and Spatio-temporal Graph Neural Networks (STAGE) for spatial relationship modeling. The system incorporates Federated Learning with Differential Privacy, Zero-Knowledge Proofs (ZKP) for authentication, and Post-Quantum Cryptography (CRYSTALS-Cyber) for blockchain-secured model updates. Experimental evaluation using real-world IoT data demonstrates a 93.4% prediction accuracy, a 12% privacy gain, and a 35% reduction in communication cost compared to traditional methods. The architecture is scalable, modular, and designed to support real-time, privacy-sensitive environmental monitoring in smart city applications.
The interest in blockchain for Industry 4.0 applications and the integration of the Industrial Internet of Things (IIoT) has grown considerably. This is due to the unique characteristics of blockchain, including the immutability of the distributed ledger, transparency, traceability of transactions, and security based on cryptographic techniques that certify the integrity of the data. So, the integration of blockchain can enhance data integrity, transparency, and security while eliminating trusted third parties. However, these characteristics make blockchains difficult to scale and typically involve high costs for a large number of transactions. It makes it difficult to manage large amounts of data which are generally produced in IIoT environments. Some recent results have demonstrated how the use of private blockchains can improve the issues of scalability and transaction costs. This paper addresses the following research question: Can blockchain technology, in its current state, be suitable for implementing industrial monitoring applications that use IIoT devices? Our objective is to propose a blockchain-based application integrated with IIoT devices in order to control the air and water pollution produced by industrial activities. The application we propose complies with current European regulations. Finally, we perform an empirical evaluation of the solution's performance to understand its applicability in real-world scenarios.
Montaser N.A. Ramadan, Mohammed A. H. Ali, Hadi Jaber, Mohammad Alkhedher
Air pollution in industrial zones significantly impacts environmental safety and worker health. This paper presents a novel decentralized IoT-federated learning (FL) framework, uniquely integrated with blockchain security, designed to provide a mechanistic understanding and accurate predictive modeling of air pollutant exposure in industrial environments. The novelty lies in the integration of a hybrid EMD-Transformer-BiLSTM prediction model with a blockchain-backed federated learning mechanism, providing secure, tamper-proof decentralized model updates. Three IoT-based sensing units, deployed across an industrial facility for five months, continuously monitored pollutants (PM2.5, PM10, CO₂, VOCs, CH₂O, CO, and O₃) and environmental factors (temperature, humidity). The innovative model improved prediction accuracy from 83.12 % to 92.5 % for short-term (5-minute) forecasts, stabilizing at 84.7 % for 60-minute predictions after 15 FL rounds. Model validation indicated strong predictive reliability (R² = 0.89), significantly reducing prediction errors (Mean Absolute Error and Root Mean Square Error). Blockchain integration successfully ensured data integrity, identifying and rejecting over 98.7 % of unauthorized updates. Additionally, a swarm intelligence approach optimized decentralized model aggregation, minimizing communication overhead despite increased security latency (FL rounds increased from 7.5 s to 13.5 s for 500 clients). Real-time RGB-based air quality index visualization and cloud-based spatio-temporal mapping provided actionable insights into pollutant dynamics. This study demonstrates a distinct advancement in air pollution monitoring by combining federated learning, blockchain technology, and real-time adaptive visualization for enhanced environmental safety in industrial settings.
A pressing challenge in verifiable monitoring of anthropogenic impacts on the environment under conditions of intensive industrialization lies in the development of conceptual approaches to designing architectures of secure sensor systems that integrate cryptographic authentication, distributed verification, and blockchain technologies. The SmartDust concept, which envisages the deployment of distributed sensor swarms composed of micro-electromechanical systems, demonstrates considerable potential for building scalable ecological and analytical infrastructures. However, unresolved issues remain with respect to ensuring the cryptographic authenticity of sensor nodes, protecting telemetry data from tampering, and maintaining resilience against cyber-physical attacks and electromagnetic interference. This article proposes a conceptual architecture grounded in a multi-layered paradigm of trusted interaction. The architectural model incorporates cryptographic identification and lightweight digital signing of telemetry packets at the sensor level, swarm-based cross-verification of data using decentralized consensus algorithms, and the integration of gateways with a distributed ledger to guarantee data immutability and retrospective verifiability. Simulation results indicate that the proposed architecture substantially enhances the trustworthiness of environmental monitoring data, minimizes the risks of data falsification, and ensures the resilience of the sensor network to disruptive influences.
The increasing complexity of modern aircraft systems necessitates advanced monitoring solutions to ensure operational safety and efficiency. Traditional aircraft health monitoring systems (AHMS) often rely on reactive maintenance strategies, detecting only visible faults while leaving underlying issues unaddressed. This gap can lead to critical failures and unplanned downtime, resulting in significant operational costs. To address this issue, this paper proposes the integration of artificial intelligence (AI) and blockchain technologies within an enhanced AHMS, utilizing the iceberg model as a conceptual framework to illustrate both visible and hidden defects. The model highlights the importance of detecting and addressing issues at the earliest possible stages, ensuring that hidden defects are identified and mitigated before they evolve into significant failures. The rationale behind this approach lies in the need for a predictive maintenance system capable of identifying and mitigating hidden risks before they escalate. Key tasks completed in this study include: a comparative analysis of the proposed system with existing monitoring solutions, the selection of AI algorithms for fault prediction, and the development of a blockchain-based infrastructure for secure, transparent data sharing. The evolution of AHMS is discussed, emphasizing the shift from traditional monitoring to advanced, predictive, and prescriptive maintenance approaches. This integrated approach demonstrates the potential to significantly improve fault detection, optimize maintenance schedules, and enhance data security across the aviation industry.
Ahmed Kamel Abdelghany Hassan, Mohamed S. Saraya, Amr M. T. Ali-Eldin, Mohamed M. Abdelsalam
Air pollution is a growing concern due to severe threats to public health and the environment. The need for reliable air quality monitoring solutions has never been more critical. This research paper introduces an innovative approach to addressing this challenge by deploying a low-cost Internet of Things (IoT) air monitoring station and providing a blockchain technology solution to enhance environmental data transparency, reliability, and accessibility. Our paper adopts a concept of merging IoT and blockchain technologies and collecting some parameters that help to assess air quality by using three sensors, DHT11, MQ7, and MQ135, to collect temperature, humidity, carbon monoxide, and carbon dioxide parameters, respectively, to measure the gases and thus indicate the air quality within the surrounding area. Collecting and sharing these types of valuable data will be very important for various stakeholders, such as governmental bodies, researchers, and the public. This approach is consistent with the principles of sustainable development, facilitating informed decision-making and promoting eco-friendly policies. This research explores the technical architecture of the IoT air monitoring stations, offering a promising solution for addressing air pollution concerns while promoting sustainable development goals. The proposed system is a model for leveraging emerging technologies to advance environmental monitoring and create smarter, livable cities. This approach aligns with the principles of sustainable development and eco-friendly initiatives. This research offers a promising model for enhancing environmental monitoring efforts and advancing the creation of smarter, more sustainable urban environments. The proposed IoT, cloud platform and blockchain-based system not only addresses pressing air pollution challenges but also sets a benchmark for leveraging emerging technologies in environmental science.
Amit Kumar, Neha Sharma, Rahul Chauhan, Manish Sharma
The present research utilizes Topic Modelling as a methodology to acquire a deeper understanding of the goals and operations of Decentralised Autonomous Organisations (DAOs). This is achieved by examining textual data derived from the proposals put forth by these organizations. The issue at hand pertains to comprehending the multitude of ideas inside Decentralised Autonomous Organisations (DAOs) and their alignment with the respective objectives of these entities. Through the application of Topic Modelling, we aim to investigate textual patterns, identify topics, and discern significant themes within the decentralized autonomous organization (DAO) ecosystem. This research endeavor seeks to address the existing research gaps pertaining to the alignment of proposals with organizational objectives. This research aims to fill these knowledge gaps by examining the unique thematic priorities of various decentralized autonomous organizations (DAOs), providing insights into their functions, and elucidating their involvement in investment, community, technological, and monetary issues. Through the utilization of experimental research, this research provides DAO stakeholders with the ability to make wellinformed judgements, prioritize ideas, and customize methods in order to more effectively match with their distinct missions and objectives. Consequently, this research contributes to the enhancement of operational efficiency and governance within DAOs.
<title>Abstract</title> The delivery and management of clean water are crucial for the long-term growth of Smart Cities. However, controlling water quality and delivery in a smart city is a difficult and time-consuming process. In this work, we suggest a unique solution for smart water quality monitoring and distribution in Smart Cities that combines Internet of Things (IoT) with blockchain technology. We describe a system based on Hyperledger Fabric that provides safe and efficient data gathering, authentication, preservation, and smart contract execution. A continuous monitoring of water quality parameters, such as pH, temperature, turbidity, and dissolved oxygen, is achieved using the proposed IoT system. The collected data is stored on a secure blockchain ledger using Hyperledger Fabric, ensuring transparency, immutability, and security. Smart contracts are used to automate the water distribution process, enabling the system to efficiently allocate water resources based on demand and quality. Furthermore, the use of blockchain technology ensures that water quality data cannot be tampered with, providing a high degree of trust and accountability in the system. Overall, the proposed system represents a significant step towards a sustainable and secure future for water management in cities. This technology can revolutionize the way we manage and distribute water resources, ensuring safe and clean drinking water for future generations.
In the era of Industry 4.0, automated remote monitoring of environmental conditions is based on the use of IoT sensors controlled by various wireless technologies. Registering the moment of occurrence of unwanted and unexpected events is extremely important, both for taking adequate actions to limit the damage and for proving the responsibility of certain employees, but also for presenting an insurance claim to the insurance company with irrefutable evidence. This paper presents a model and solution based on HyperLedger blockchain and IoT sensor network integrating BLE, LoRa and ZigBee technologies. The presented studies prove the applicability of the proposed model and the advantages it offers - trust, transparency, security, visibility and role-based access to all participants in the business network.
The rapid pace of development of the Internet of Things and the requirements of various devices have allowed us to perform calculations at the edge, especially in terms of consumer electronics. Such progress makes it possible to design new solutions for energy distribution and prediction for smart homes. In this paper, we propose a solution that can be used to optimize energy distribution by analyzing the energy demand in individual homes. The proposed methodology is based on edge technology, where a dedicated LSTM network with a multi-head self-attention network is trained with measurement data from different sensors for predicting energy demand. Training of this network is extended to a decentralized learning process with an additional aggregation decision module (that allows rejection of the model in case of worst adaptation to private data). In order to increase data security, we added a blockchain network with a Byzantine strategy and Proof of Stake (PoS) consensus. The solution was tested for a publicly available database in order to demonstrate the possibilities and advantages of such an architecture.
Ethereum is a major public blockchain. Besides being the second-largest digital currency by market capitalization for its cryptocurrency, the Ether (Ξ), it is also the foundation of Web3 and decentralized applications, or DApps, that are fuelled by Smart Contracts. At the time of this writing, Ethereum still uses Proof of Work (PoW) consensus algorithm to ensure the integrity of the blockchain and to prevent double spend. PoW requires the participation of miners, who are incentivized to assemble blocks of transactions by being rewarded with cryptocurrency paid by transaction originators and by the blockchain network itself via newly minted Ξ. Network fees for transaction submissions are called gas, by analogy to the fuel used by cars, and are negotiable. They are also highly volatile and hence it is critical to predict the direction they are heading into, so that one can time transaction submissions, when feasible. There have been several efforts to predict gas prices, including usage of large Mempools, analysis of committed blocks, and more recent ones using Facebook's Prophet model [Taylor, S. J., & Letham, B. (2017). Forecasting at scale. PeerJ Preprints, 5, e3190v2. https://doi.org/10.7287/peerj.preprints.3190v2]. In this study, we introduce an innovative approach that employs the DeepAR [Salinas, D., Flunkert, V., Gasthaus, J., & Januschowski, T. (2020). Deepar: Probabilistic forecasting with autoregressive recurrent networks. International Journal of Forecasting, 36(3), 1181–1191. https://doi.org/10.1016/j.ijforecast.2019.07.001] model, known for its superior forecasting accuracy over conventional methods by virtue of its ability to learn from multiple related time series. This methodology not only offers immediate advantages but also holds promise for ongoing enhancements. We substantiate our claims through empirical testing, utilizing data extracts from the Ethereum blockchain and cryptocurrency price feeds. This document is an extended version of our ICCS 2022 paper on the same topic. In this paper, we dive deeper into the internals of DeepAR forecasting algorithm [Salinas, D., Flunkert, V., Gasthaus, J., & Januschowski, T. (2020). Deepar: Probabilistic forecasting with autoregressive recurrent networks. International Journal of Forecasting, 36(3), 1181–1191. https://doi.org/10.1016/j.ijforecast.2019.07.001], analyse the correlation between the on-chain/off-chain sample data, and describe additional experiments that empirically prove our findings and, finally, perform a comparison of our outputs with those from the Prophet [Taylor, S. J., & Letham, B. (2017). Forecasting at scale. PeerJ Preprints, 5, e3190v2. https://doi.org/10.7287/peerj.preprints.3190v2] model.
Nan Ma, Alex Waegel, Max Hakkarainen, William W. Braham · 6 authors
Electric demand flexibility in buildings is highly dependent on occupant behavior. Evaluating and incentivizing these behaviors can provide grid-responsive support and encourage demand response (DR) participation. To achieve these goals, we developed an infrastructure for connecting Internet of Things (IoT) sensors to a distributed ledger (blockchain network) for long-term monitoring of energy and environmental performance. This study presents a novel Blockchain + IoT paradigm for the building science research community, applied in a real-world application. This Blockchain + IoT Network (BIN) uses Raspberry Pi minicomputers as platforms for connecting sensors to a blockchain network, to provide and analyze real-time indoor environmental quality (IEQ), energy, and carbon intensity data. As part of the study, we propose various metrics to evaluate the environmental footprints of building users. Novel algorithms for normalizing energy usage and carbon intensity, with consideration of a variety of related environmental factors, are executed as smart contracts on the blockchain network. All measurements and the smart contract transactions are reported and visualized on live dashboards. The use of smart contract allocates tokens based on the reward algorithms to incentivize individuals’ energy conservation, and similarly to DR pricing, can help influence occupant consumption patterns towards carbon reduction goals. We further test the smart contract’s algorithm in relation to real sensor data we have collected in two case studies: single-unit households and carbon intensity in the energy market. The combination of proposed metrics translates measured sensor data into token awards, demonstrates upper and lower limits dictated by the grid generation mix profile, and indicates that there is the potential for load shifting to minimize carbon emissions without considering the scale of consumption.
The cumulative amount of greenhouse gases that are shaped by our actions is a carbon footmark. In the US, the total carbon footmark of a humanoid is 16 tonnes, one of the largest amounts in the world. The average is closer to 4 tonnes worldwide. The average universal carbon footmark per year requirements is to drop below 3 tonnes by 2050 to have the utmost chance of stopping a 2°C point rise in worldwide temperature. Rahul et al. already predicted that the carbon footprint reduced by 17% with the use of IoT-enabled services. In this research study a novel approach to reduce carbon footprint using IoT with reinforcement AI learning is presented, which further reduced carbon footprint by 5% when using and nearly 7% when it is done using Q-Learning. The detailed findings are included to demonstrate the result.