ObjectiveCompared with traditional concrete construction, the application of prefabricated assembly construction based on digital twin technology in urban rail transit station construction can effectively ensure component production quality, reduce environmental pollution and lower resource consumption. Therefore, an in-depth research on digital twin technology suitable for prefabricated assembly station construction should be conducted. MethodFirst, in station construction, the overall architecture featuring "4 horizontal + 4 vertical + N platforms" for the application of digital twin technologies, such as BIM (building information modeling) and IoT (Internet of things) is proposed. Second, the modeling process and methodology of BIM are presented. By adopting methods such as mathematical model separation, lightweight processing, and mathematical model association, the established BIM data are imported into the platform, and a technical workflow for uploading IoT monitoring data to the BIM platform is established. Finally, taking a certain underground prefabricated assembly superimposed station in the Phase I project of Jinan Urban Rail Transit Line 8 as a case study, the application effect of the digital twin technology for prefabricated assembly superimposed stations based on BIM+IoT integration is analyzed. Result & Conclusion The proposed digital twin technology shows good application effects in the case station, achieving design goals such as construction progress query, structural safety monitoring, quality management control, and process auxiliary design, and realizing data management interaction and sharing throughout the components full life cycle.
The rapid integration of AI into IoT systems has outpaced the ability to explain and audit automated decisions, resulting in a serious transparency gap. We address this challenge by proposing a blockchain-based framework to create immutable audit trails of AI-driven IoT decisions. In our approach, each AI inference comprising key inputs, model ID, and output is logged to a permissioned blockchain ledger, ensuring that every decision is traceable and auditable. IoT devices and edge gateways submit cryptographically signed decision records via smart contracts, resulting in an immutable, timestamped log that is tamper-resistant. This decentralized approach guarantees non-repudiation and data integrity while balancing transparency with privacy (e.g., hashing personal data on-chain) to meet data protection norms. Our design aligns with emerging regulations, such as the EU AI Act’s logging mandate and GDPR’s transparency requirements. We demonstrate the framework’s applicability in two domains: healthcare IoT (logging diagnostic AI alerts for accountability) and industrial IoT (tracking autonomous control actions), showing its generalizability to high-stakes environments. Our contributions include the following: (1) a novel architecture for AI decision provenance in IoT, (2) a blockchain-based design to securely record AI decision-making processes, and (3) a simulation informed performance assessment based on projected metrics (throughput, latency, and storage) to assess the approach’s feasibility. By providing a reliable immutable audit trail for AI in IoT, our framework enhances transparency and trust in autonomous systems and offers a much-needed mechanism for auditable AI under increasing regulatory scrutiny.
Anjana M S, Aryadevi Remanidevi Devidas, Maneesha Vinodini Ramesh
Electrical energy plays a pivotal role in modern society by powering homes, industries, and transportation systems. However, the production of electricity is associated with significant carbon emissions, primarily from fossil fuel-based power generation, and there is 1.1% rise in carbon emissions by 2023 compared to 2022. Mitigating carbon emissions from electrical energy is a critical global challenge that requires a multifaceted approach. Transitioning to cleaner energy sources and improving energy efficiency are essential steps to reduce the environmental impact of electricity generation. Energy management is crucial to reduce energy consumption effectively. So this study proposes a Multi-Model Energy Management System (MEnMS) integrated with a Fractal Internet of Things (IoT) architecture to address enhanced energy management by reducing energy usage, and carbon footprint. The study conducts a detailed energy consumption analysis across distinct cases. From the analysis, it can be seen that an average of 25% of energy can be saved with MEnMS without IoT energy overhead. Key observations include, EnMS with IoT devices and automation offers smartness, they do not lead to a significant reduction in energy consumption. Moreover, these IoT devices and centralized learning consume more energy. However, integrating IoT devices with distributed learning and multiple models significantly reduces energy consumption as well as the carbon footprint. The analysis reveals that the MEnMS system outperforms alternative approaches, particularly at higher occupancy levels, establishing itself as the most efficient energy management solution. At an occupancy level of 25 users, it achieves an impressive 8% reduction in energy consumption compared to the Traditional System, showcasing its unique capability to scale energy savings as occupancy increases. This innovative system combines advanced local processing with EQC optimization, providing a cutting-edge approach to sustainable energy management in high-occupancy scenarios. Furthermore, the algorithms driving occupant-centric automation and the indoor localization method demonstrate remarkable performance, achieving an efficiency of 92% and an accuracy of 90%, respectively. Therefore, the MEnMs framework can be used to monitor energy usage thereby reducing energy consumption, which results in a low-carbon footprint. By tracking the activity, the occupants get a clear understanding of their carbon footprint and they can make adjustment to reduce carbon emissions.
Recently, the Internet of Things (IoT) has played an important role in many fields. Nevertheless, the fast and uneven energy consumption of IoT Devices (IoTDs) significantly limits the lifetime of IoT networks. One of the effective solutions is to deploy Laser Static Chargers (LSCs) to power IoTDs. However, deploying LSCs to cover all IoTDs will consume enormous costs. To prolong the lifetime of IoT and reduce the deployment costs of LSCs, in this paper, we first propose a novel IoT network named Self-organizing Power Transfer IoT with Laser Static Chargers (SPTIoT-LSC), where IoTDs are equipped with laser transmission and reception modules allowing energy transfer between IoTDs, and several LSCs are deployed into the network to charge IoTDs. Based on SPTIoT-LSC, we study the Minimizing Laser Chargers Coverage(MLCC) problem, which aims to minimize the number of LSCs deployed in SPTIoT-LSC while enabling all IoTDs to work continuously. Then we prove its NP-hardness. To solve the problem, we propose two sub-algorithms: the Layered Charging Scheduling Strategy (LCSS) algorithm and Deploy Chargers based on the Multi-agent deep deterministic policy gradient (DCM) algorithm to maximize the working time of IoTDs with given LSCs and corresponding positions and deploy given LSCs in SPTIoT-LSC, respectively. Based on the above sub-algorithms, we propose an approximation algorithm to solve the MLCC problem. Finally, extensive experiments are proposed to verify the efficiency of the proposed algorithm and the superiority of SPTIoT-LSC.
The growing adoption of IoT applications has led to increased use of low-power microcontroller units (MCUs) for energy-efficient, local data processing. However, deploying deep neural networks (DNNs) on these constrained devices is challenging due to limitations in memory, computational power, and energy. Traditional methods like cloud-based inference and model compression often incur bandwidth, privacy, and accuracy trade-offs. This paper introduces a novel Decentralized Distributed Sequential Neural Network (DDSNN) designed for low-power MCUs in Tiny Machine Learning (TinyML) applications. Unlike the existing methods that rely on centralized cluster-based approaches, DDSNN partitions a pre-trained LeNet across multiple MCUs, enabling fully decentralized inference in wireless sensor networks (WSNs). We validate DDSNN in a real-world predictive maintenance scenario, where vibration data from an industrial pump is analyzed in real-time. The experimental results demonstrate that DDSNN achieves 99.01% accuracy, explicitly maintaining the accuracy of the non-distributed baseline model and reducing inference latency by approximately 50%, highlighting its significant enhancement over traditional, non-distributed approaches, demonstrating its practical feasibility under realistic operating conditions.
Simone Figorilli, Lavinia Moscovini, Simone Vasta
et al.
Recently banana plantations have been affected by the Black Sigatoka Disease (BSD), producing streaks, lesions and yellow and brown spots on the leaves until the appearance of entire dead parts. The disease causes reductions in yield making it essential to assess infection by monitoring plants status and implementing agronomical measures. This work aims to develop a physical field device to identify the BSD presence. It consists in a 3D printed prototype embedding a smartphone acquiring and processing banana leaves images. An advanced Artificial Intelligence model was trained and implemented for real-time processing. The algorithm is a Convolutional Neural Network (CNN) able to classify the samples into 6 classes representative of different BSD stages infection. The trained model, showing an accuracy of 82 % in training and 78 % in validation, was integrated into a specifically developed mobile application for field use. The Android app allows to acquire, identify the georeferenced infection stage, sync all to a remote dedicated host from which the results can be mapped and exported to a .csv file for easy data management. The distinction between healthy and diseased leaves can be achieved using the Smart BSD device for real-time acquisition, establishing the right intervention strategy.
Abstract This paper presents novel MIMO microstrip patch antennas with dimensions of 40 × 80 × 1.6 mm³ incorporating a decoupling and pattern correction structure (DPCS) designed to mitigate mutual coupling and radiation pattern distortion, operating within 3.6–3.7 GHz. Using characteristic mode analysis (CMA), two key modes affecting coupling and pattern degradation are identified, with the DPCS strategically positioned to address these issues. Unlike other decoupling techniques, the DPCS requires no additional space or structural complexity, making it suitable for 5G MIMO systems. The proposed design achieves isolation up to 90 dB and enhances the realized gain of Port 2 by 3 dB at boresight in simulations. Fabricated antennas were measured, achieving peak isolation of 80 dB in an anechoic chamber. Additionally, measurements in a noisy environment confirmed the robustness of the design under realistic conditions. Measured radiation patterns verified the DPCS’s ability to correct the radiation pattern. Key MIMO performance metrics, including ECC (2 × 10⁻⁴), DG (≈ 10), CCL (< 0.2 bits/s/Hz), MEG (≈ -7 dB), and TARC (< -12 dB), affirmed the design’s superior performance. The proposed structure can be applied to a variety of applications such as high-density urban wireless networks and IoT systems, where maintaining high isolation and reliable communication are critical requirements.
Ammad Aslam, Octavian Postolache, Sancho Oliveira
et al.
Sharding is an emerging blockchain technology that is used extensively in several fields such as finance, reputation systems, the IoT, and others because of its ability to secure and increase the number of transactions every second. In sharding-based technology, the blockchain is divided into several sub-chains, also known as shards, that enhance the network throughput. This paper aims to examine the impact of integrating sharding-based blockchain network technology in securing IoT sensors, which is further used for environmental monitoring. In this paper, the idea of integrating sharding-based blockchain technology is proposed, along with its advantages and disadvantages, by conducting a systematic literature review of studies based on sharding-based blockchain technology in recent years. Based on the research findings, sharding-based technology is beneficial in securing IoT systems by improving security, access, and transaction rates. The findings also suggest several issues, such as cross-shard transactions, synchronization issues, and the concentration of stakes. With an increased focus on showcasing the important trade-offs, this paper also offers several recommendations for further research on the implementation of blockchain network technology for securing IoT sensors with applications in environment monitoring. These valuable insights are further effective in facilitating informed decisions while integrating sharding-based technology in developing more secure and efficient decentralized networks for internet data centers (IDCs), and monitoring the environment by picking out key points of the data.
Wireless sensor networks (WSNs) are widely used in IoT, environmental monitoring, and industrial systems, but ensuring energy efficiency, extended network lifetime, and reliable communication under real-world constraints remains challenging. This work proposes a novel clustering framework that integrates kernel density estimation (KDE)-based adaptive node deployment, silhouette-optimized K-means clustering, Bayesian cluster head (CH) selection with Gaussian noise-based energy uncertainty modeling, energy-efficient coverage control, and carrier sense multiple access with collision avoidance-based data transmission. Unlike conventional approaches that rely on fixed clustering and uniform deployments, our framework supports terrain-aware node placement and dynamic CH selection based on residual energy and distance under imperfect sensing conditions. Simulation results demonstrate significant improvements in performance, including over 35% extension in network lifetime and higher coverage retention under energy constraints, compared to baseline methods such as LEACH and K-LEACH. While detailed metrics vary per run due to adaptive parameters and stochastic node behavior, these outcomes validate the scalability, robustness, and practical relevance of the proposed method for real-world WSN deployments.
Jeetendra Kumar, Rashmi Gupta, Suvarna Sharma
et al.
Presents corrections to the paper, (Corrections to “IoT-Enabled Advanced Water Quality Monitoring System for Pond Management and Environmental Conservation”).
The transformation to Industry 4.0 has significantly revolutionized manufacturing and production processes, raising important questions about their impact on sustainability. This study aims to explore the interplay between Industry 4.0 and the economic, social, and environmental dimensions of sustainability. The methodological approach includes advanced text-mining, sentiment analysis, and association rule-mining techniques to examine 6,759 abstracts from the Scopus database. The text mining highlighted frequent keywords related to Industry 4.0 and the three sustainability dimensions, characterized by “economic growth,” “circular economy,” “social responsibility,” “education 4.0,” “energy efficiency,” and “waste management.” Sentiment analysis revealed a predominantly positive perspective, with 2,608 positive sentiments out of 2,761 in the economic dimension, 1,604 out of 1,728 in the social dimension, and 1,352 out of 1,527 in the environmental dimension. The association rule mining uncovered the associations between Industry 4.0 and each sustainability dimension. The highest support was observed between Industry 4.0 and economic sustainability, with a support value of 0.444, confidence of 0.855, and a lift of 1.060. These findings highlight the role of Industry 4.0 in promoting resource efficiency and reducing waste through circular economy principles and advanced manufacturing technologies. For the social dimension, the analysis revealed a strong association with Industry 4.0 (support: 0.430, confidence: 0.831, lift: 1.030), emphasizing its role in enhancing worker safety and job satisfaction by automating hazardous tasks and creating new high-tech job opportunities. In the environmental dimension, a significant association was found (support: 0.380, confidence: 0.827, lift: 1.024), showing Industry 4.0′s contribution to sustainability through optimized energy consumption and emissions reduction as the integration of big data and IoT enables real-time monitoring of environmental impacts. The rule combining economic and social aspects with Industry 4.0 (support: 0.219, confidence: 0.87, lift: 1.078) highlights the interconnected nature of these dimensions, suggesting many studies consider economic and social dimensions together in the Industry 4.0 context.
Secret sharing schemes are widely used to protect data by breaking the secret into pieces and sharing them amongst various members of a party. In this paper, our objective is to produce a repairable ramp scheme that allows for the retrieval of a share through a collection of members in the event of its loss. Repairable Threshold Schemes (RTSs) can be used in cloud storage and General Data Protection Regulation (GDPR) protocols. Secure and energy-efficient data transfer in sensor-based IoTs is built using ramp-type schemes. Protecting personal privacy and reinforcing the security of electronic identification (eID) cards can be achieved using similar schemes. Desmedt et al. introduced the concept of frameproofness in 2021, which motivated us to further improve our construction with respect to this framework. We introduce a graph theoretic approach to the design for a well-rounded and easy presentation of the idea and clarity of our results. We also highlight the importance of secret sharing schemes for IoT applications, as they distribute the secret amongst several devices. Secret sharing schemes offer superior security in lightweight IoT compared to symmetric key encryption or AE schemes because they do not disclose the entire secret to a single device, but rather distribute it among several devices.
N. Kannaiya Raja, E. Laxmi Lydia, Thumpala Archana Acharya
et al.
In recent years, drones or Unmanned Aerial Vehicles (UAVs) got significant attention among researchers because of their extensive application in commercial applications, border surveillance, etc. As the conventional terrestrial communication system does not work effectively on heavy calamities namely floods, landslides, cyclones, earthquakes, etc., UAVs can offer a potential solution for inexpensive, rapid, and wireless communication. Despite the drones’ benefits in emergency monitoring, security is been a main factor because of the existence of wireless connections for transmission. Therefore, this article introduces optimal deep learning with image encryption-based secure drone communication (ODLIE-SDC) technique. The major intention of the ODLIE-SDC technique lies in the effectual secure communication and classification process in emergency monitoring scenarios. To accomplish this, the presented ODLIE-SDC technique designs a hyperchaotic map-based image encryption technique and its optimal keys are produced by the use of a rider optimization algorithm (ROA). The image classification process is performed encompassing EfficientNet-B4-CBAM feature extraction and enhanced stacked autoencoder (ESAE) classification. Finally, the hyperparameter tuning of the EfficientNet-B4-CBAM technique takes place using the Bayesian optimization (BO) algorithm. The experimental validation of the ODLIE-SDC technique is tested on the AIDER dataset. The comprehensive comparative analysis reported the enhanced performance of the ODLIE-SDC technique over other existing approaches.
With rapid urbanization, hazardous environmental exposures such as air, noise, plastic, soil and water pollution have emerged as a major threat to urban health. Recent studies show that 9 out of 10 people worldwide breathe contaminated air contributing to over 7 million premature deaths annually. Internet of Things (IoT) and Artificial Intelligence (AI)-based environmental sensing and modelling systems have potential for contributing low-cost and effective solutions by providing timely data and insights to inform mitigation and management actions. While low and middleincome countries are among those most affected by environmental health risks, the appropriateness and deployment of IoT and AI systems in low-resource settings is least understood. Motivated by this knowledge gap, this paper presents a design space for a custom environmental sensing and management system designed and developed to fill the data gaps in low-resource urban settings with a particular focus on African cities. The paper presents the AirQo system, which is the first instance of the design space requirements. The AirQo system includes: (1) autonomous AirQo sensors designed and customised to be deployed in resource constrained environments (2) a distributed sensor network that includes over 120 static and mobile nodes for air quality sensing (3) AirQo network manager tool for tracking and management of installation and maintenance of nodes, (4) AirQo platform that provides calibration, data access and analytics tools to support usage among policy makers and citizens. Case studies from African cities that are using the data and insights for education, awareness and policy are presented. The paper provides a template for designing and deploying a technology-driven solution for cities in low resource settings.
Angela Popa, Alfonso P. Ramallo González, Gaurav Jaglan
et al.
Encouraged by the European Union, all European countries need to enforce solutions to reduce non-renewable energy consumption in buildings. The reduction of energy (heating, domestic hot water, and appliances consumption) aims for the vision of near-zero energy consumption as a requirement goal for constructing buildings. In this paper, we review the available standards, tools and frameworks on the energy performance of buildings. Additionally, this work investigates if energy performance ratings can be obtained with energy consumption data from IoT devices and if the floor size and energy consumption values are enough to determine a dwellings’ energy performance rating. The essential outcome of this work is a data-driven prediction tool for energy performance labels that can run automatically. The tool is based on the cutting edge kNN classification algorithm and trained on open datasets with actual building data such as those coming from the IoT paradigm. Additionally, it assesses the results of the prediction by analysing its accuracy values. Furthermore, an approach to semantic annotations for energy performance certification data with currently available ontologies is presented. Use cases for an extension of this work are also discussed in the end.
Mani Teja Bodduluri, Torben Dankwort, Thomas Lisec
et al.
Energy harvesting and storage is highly demanded to enhance the lifetime of autonomous systems, such as IoT sensor nodes, avoiding costly and time-consuming battery replacement. However, cost efficient and small-scale energy harvesting systems with reasonable power output are still subjects of current development. In this work, we present a mechanically and magnetically excitable MEMS vibrational piezoelectric energy harvester featuring wafer-level integrated rare-earth micromagnets. The latter enable harvesting of energy efficiently both in resonance and from low-g, low-frequency mechanical energy sources. Under rotational magnetic excitation at frequencies below 50 Hz, RMS power output up to 74.11 µW is demonstrated in frequency up-conversion. Magnetic excitation in resonance results in open-circuit voltages > 9 V and RMS power output up to 139.39 µW. For purely mechanical excitation, the powder-based integration process allows the realization of high-density and thus compact proof masses in the cantilever design. Accordingly, the device achieves 24.75 µW power output under mechanical excitation of 0.75 g at resonance. The ability to load a capacitance of 2.8 µF at 2.5 V within 30 s is demonstrated, facilitating a custom design low-power ASIC.
Dhanalekshmi Prasad Yedurkar, Shilpa P. Metkar, Fadi Al-Turjman
et al.
A novel approach for multichannel epilepsy seizure classification which will help to automatically locate seizure activity present in the focal brain region was proposed. This paper suggested an Internet of Things (IoT) framework based on a smart phone by utilizing a novel feature termed multiresolution critical spectral verge (MCSV), based on frequency-derived information for epileptic seizure classification which was optimized using a flower pollination algorithm (FPA). A wireless sensor technology (WSN) was utilized to record the electroencephalography (EEG) signal of epileptic patients. Next, the EEG signal was pre-processed utilizing a multiresolution-based adaptive filtering (MRAF) method. Then, the maximal frequency point at which the power spectral density (PSD) of each EEG segment was greater than the average spectral power of the corresponding frequency band was computed. This point was further optimized to extract a point termed as critical spectral verge (CSV) to extract the exact high frequency oscillations representing the actual seizure activity present in the EEG signal. Next, a support vector machine (SVM) classifier was used for channel-wise classification of the seizure and non-seizure regions using CSV as a feature. This process of classification using the CSV feature extracted from the MRAF output is referred to as the MCSV approach. As a final step, cloud-based services were employed to analyze the EEG information from the subject’s smart phone. An exhaustive analysis was undertaken to assess the performance of the MCSV approach for two datasets. The presented approach showed an improved performance with a 93.83% average sensitivity, a 97.94% average specificity, a 97.38% average accuracy with the SVM classifier, and a 95.89% average detection rate as compared with other state-of-the-art studies such as deep learning. The methods presented in the literature were unable to precisely localize the origination of the seizure activity in the brain region and reported a low seizure detection rate. This work introduced an optimized CSV feature which was effectively used for multichannel seizure classification and localization of seizure origination. The proposed MCSV approach will help diagnose epileptic behavior from multichannel EEG signals which will be extremely useful for neuro-experts to analyze seizure details from different regions of the brain.