IoT

In various applications, IoT temporal data play a crucial role in accurately predicting future trends. Traditional models, including Rolling Window, SVR-RBF, and ARIMA, suffer from a potential accuracy decrease because they generally use all available data or the most recent data window during training, which can result in the inclusion of noisy data. To address this critical issue, this paper proposes a new forecasting technique called Adaptive Holt–Winters (AHW). The AHW approach utilizes two models grounded in an exponential smoothing methodology. The first model is trained on the most current data window, whereas the second extracts information from a historical data segment exhibiting patterns most analogous to the present. The outputs of the two models are then combined, demonstrating enhanced prediction precision since the focus is on the relevant data patterns. The effectiveness of the AHW model is evaluated against well-known models (Rolling Window, SVR-RBF, ARIMA, LSTM, CNN, RNN, and Holt–Winters), utilizing various metrics, such as RMSE, MAE, p-value, and time performance. A comprehensive evaluation covers various real-world datasets at different granularities (daily and monthly), including temperature from the National Climatic Data Center (NCDC), humidity and soil moisture measurements from the Basel City environmental system, and global intensity and global reactive power from the Individual Household Electric Power Consumption (IHEPC) dataset. The evaluation results demonstrate that AHW constantly attains higher forecasting accuracy across the tested datasets compared to other models. This indicates the efficacy of AHW in leveraging pertinent data patterns for enhanced predictive precision, offering a robust solution for temporal IoT data forecasting. Full article

This paper presents a novel video encoding and decoding method aimed at enhancing security and reducing storage requirements, particularly for CCTV systems. The technique merges two video streams of matching frame dimensions into a single stream, optimizing disk space usage without compromising video quality. The combined video is secured using an advanced encryption standard (AES)-based shift algorithm that rearranges pixel positions, preventing unauthorized access. During decoding, the AES shift is reversed, enabling precise reconstruction of the original videos. This approach provides a space-efficient and secure solution for managing multiple video feeds while ensuring accurate recovery of the original content. The experimental results demonstrate that the transmission time for the encoded video is consistently shorter compared to transmitting the video streams separately. This, in turn, leads to about $54\%$ reduction in energy consumption across diverse outdoor and indoor video datasets, highlighting significant improvements in both transmission efficiency and energy savings by our proposed scheme. Full article

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. Full article

With the advent of Industry 4.0, sensor-based human activity recognition has become increasingly vital for improving worker safety, enhancing operational efficiency, and optimizing workflows in Internet-of-Things (IoT) environments. This study introduces a novel deep learning-based framework for construction worker activity recognition, employing a deep residual convolutional neural network (ResNet) architecture integrated with multi-sensor fusion techniques. The proposed system processes data from multiple inertial measurement unit sensors strategically positioned on workers’ bodies to identify and classify construction-related activities accurately. A comprehensive pre-processing pipeline is implemented, incorporating Butterworth filtering for noise suppression, data normalization, and an adaptive sliding window mechanism for temporal segmentation. Experimental validation is conducted using the publicly available VTT-ConIoT dataset, which includes recordings of 16 construction activities performed by 13 participants in a controlled laboratory setting. The results demonstrate that the ResNet-based sensor fusion approach outperforms traditional single-sensor models and other deep learning methods. The system achieves classification accuracies of 97.32% for binary discrimination between recommended and non-recommended activities, 97.14% for categorizing six core task types, and 98.68% for detailed classification across sixteen individual activities. Optimal performance is consistently obtained with a 4-second window size, balancing recognition accuracy with computational efficiency. Although the hand-mounted sensor proved to be the most effective as a standalone unit, multi-sensor configurations delivered significantly higher accuracy, particularly in complex classification tasks. The proposed approach demonstrates strong potential for real-world applications, offering robust performance across diverse working conditions while maintaining computational feasibility for IoT deployment. This work advances the field of innovative construction by presenting a practical solution for real-time worker activity monitoring, which can be seamlessly integrated into existing IoT infrastructures to promote workplace safety, streamline construction processes, and support data-driven management decisions. Full article

Federated Learning (FL) enables decentralized Machine Learning (ML), focusing on preserving data privacy, but faces a unique set of optimization challenges, such as dealing with non-IID data, communication overhead, and client drift. Adaptive optimizers like AdaGrad, Adam, and Adam variations have been applied in FL, showing good results in convergence speed and accuracy. However, it can be quite challenging to combine good convergence, model generalization, and stability in an FL setup. Data-bound adaptive methods like AdaDB have demonstrated promising results in centralized settings by incorporating dynamic, data-dependent bounds on Learning Rates (LRs). In this paper, FedAdaDB is introduced, which is an FL version of AdaDB aiming to address the aforementioned challenges. FedAdaDB uses the AdaDB optimizer at the server-side to dynamically adjust LR bounds based on the aggregated client updates. Extensive experiments have been conducted comparing FedAdaDB with FedAvg and FedAdam on three different datasets (EMNIST, CIFAR100, and Shakespeare). The results show that FedAdaDB consistently offers better and more robust outcomes, in terms of the measured final validation accuracy across all datasets, for a trade-off of a small delay in the convergence speed at an early stage. Full article

The Message Queuing Telemetry Transport (MQTT) protocol remains a key enabler for lightweight and low-latency messaging in Internet of Things (IoT) applications. However, traditional broker implementations often struggle with the demands of large-scale point-to-point (P2P) communication. This paper presents a performance and architectural evaluation of TBMQ, an open source MQTT broker designed to support reliable P2P messaging at scale. The broker employs Redis Cluster for session persistence and Apache Kafka for message routing. Additional optimizations include asynchronous Redis access via Lettuce and Lua-based atomic operations. Stepwise load testing was performed using Kubernetes-based deployments on Amazon EKS, progressively increasing message rates to 1 million messages per second (msg/s). The results demonstrate that TBMQ achieves linear scalability and stable latency as the load increases. It reaches an average throughput of 8900 msg/s per CPU core, while maintaining end-to-end delivery latency within two-digit millisecond bounds. These findings confirm that TBMQ’s architecture provides an effective foundation for reliable, high-throughput messaging in distributed IoT systems. Full article

This paper analyzes the process of energy transition from traditional solid fuel heating to an air-to-air (A2A) heat pump-based heating system. Special emphasis was placed on the implementation of new technologies for improved management of energy systems, aiming to elevate both comfort levels and energy efficiency. This paper explores the use of the open-source software Home Assistant as an integration platform for home automation, designed to manage smart home devices while preserving local control, user privacy, and increasing cybersecurity. The proposed hardware platform includes a Raspberry Pi with appropriate IoT modules, providing a flexible and economically viable solution for household needs. Full article

Modern commercial poultry farming typically occurs indoors, where partial or complete environmental control is employed to enhance production efficiency. Maintaining optimal conditions, such as temperature, relative humidity, carbon dioxide, and ammonia levels, is essential for ensuring bird comfort and maximizing productivity. Monitoring the conditions of poultry houses requires reliable and intelligent management systems. This study introduces a Wireless Monitoring and Control System developed to regulate environmental conditions within poultry facilities. The system continuously monitors key parameters via a network of distributed sensor nodes, which transmit data wirelessly to a centralized control unit using Wi-Fi. The control unit processes the incoming data, stores it in a database, and adjusts actuators accordingly to maintain ideal conditions. A web-based dashboard allows users to monitor and control the environment in real time. Field testing confirmed the system’s effectiveness in keeping conditions optimal, supporting poultry welfare and operational efficiency. Full article

Access control systems protect homes and businesses in the continually evolving security industry. This paper designs and implements a Raspberry Pi-based facial recognition door lock system using artificial intelligence and computer vision for reliability, efficiency, and usability. With the Raspberry Pi as its CPU, the system uses facial recognition for authentication. A camera module for real-time image capturing, a relay module for solenoid lock control, and OpenCV for image processing are essential. The system uses the DeepFace library to detect user emotions and adaptive learning to improve recognition accuracy for approved users. The device also adapts to poor lighting and distances, and it sends real-time remote monitoring messages. Some of the most important things that have been achieved include adaptive facial recognition, ensuring that the system changes as it is used, and integrating real-time notifications and emotion detection without any problems. Face recognition worked well in many settings. Modular architecture facilitated hardware–software integration and scalability for various applications. In conclusion, this study created an intelligent facial recognition door lock system using Raspberry Pi hardware and open-source software libraries. The system addresses traditional access control limits and is practical, scalable, and inexpensive, demonstrating biometric technology’s potential in modern security systems. Full article

Medical image classification often relies on CNNs to capture local details (e.g., lesions, nodules) or on transformers to model long-range dependencies. However, each paradigm alone is limited in addressing both fine-grained structures and broader anatomical context. We propose ConvTransGFusion, a hybrid model that fuses ConvNeXt (for refined convolutional features) and Swin Transformer (for hierarchical global attention) using a learnable dual-attention gating mechanism. By aligning spatial dimensions, scaling each branch adaptively, and applying both channel and spatial attention, the proposed architecture bridges local and global representations, melding fine-grained lesion details with the broader anatomical context essential for accurate diagnosis. Tested on four diverse medical imaging datasets—including X-ray, ultrasound, and MRI scans—the proposed model consistently achieves superior accuracy, precision, recall, F1, and AUC over state-of-the-art CNNs and transformers. Our findings highlight the benefits of combining convolutional inductive biases and transformer-based global context in a single learnable framework, positioning ConvTransGFusion as a robust and versatile solution for real-world clinical applications. Full article

The rise of wearable devices has enabled real-time processing of sensor data for critical health monitoring applications, such as human activity recognition (HAR) and cardiac disorder classification (CDC). However, the limited computational and memory resources of wearables necessitate lightweight yet accurate classification models. While deep neural networks (DNNs), including convolutional neural networks (CNNs) and long short-term memory networks, have shown high accuracy for HAR and CDC, their large parameter sizes hinder deployment on edge devices. On the other hand, various DNN compression techniques have been proposed, but exploiting the combination of various compression techniques with the aim of achieving memory efficient DNN models for HAR and CDC tasks remains under-investigated. This work studies the impact of CNN architecture parameters, focusing on the convolutional and dense layers, to identify configurations that balance accuracy and efficiency. We derive two versions of each model—lean and fat—based on their memory characteristics. Subsequently, we apply three complementary compression techniques: filter-based pruning, low-rank factorization, and dynamic range quantization. Experiments across three diverse DNNs demonstrate that this multi-faceted compression approach can significantly reduce memory and computational requirements while maintaining validation accuracy, leading to DNN models suitable for intelligent health monitoring on resource-constrained wearable devices. Full article

Recently, electromagnetic wireless power transfer (WPT) has emerged as a promising technology for supplying power to multiple terminals. Previous studies have devised packet transmission methods, commonly used in telecommunication, for power analysis. This study develops a simulator that calculates the received power by integrating a power–packet conversion method, based on previous research. The simulator incorporates several scheduling functions to facilitate the investigation of the efficiency of the power-feeding methods. This study analyzes the efficacy of a first-come–first-served (FCFS) method, a round-robin (RR) method, and a multilevel feedback queue (MFQ) scheme for wireless power transfer, all of which were devised based on existing scheduling methods used in operating systems. Simulation results show that, although the FCFS method is simple, it may lead to battery depletion due to delayed power supply, particularly in terminals with lower initial battery levels. The RR method improves fairness by allocating the power supply in time slices; however, its performance is sensitive to the slice duration. The MFQ method, which incorporates a promotion mechanism based on battery status and power demand, exhibits higher adaptability, achieving efficient and balanced power distribution even when terminals differ in distance from the transmitter or in power consumption. These evaluations were conducted using a proposed power–packet conversion method that discretizes continuous power into packet units, allowing for the application of communication network-inspired scheduling and control techniques. The capacity to construct such models enables the simulator to analyze the flow and distribution of power, predict potential issues that may arise in real systems in advance, and devise optimal control methodologies. Moreover, the model can be employed to enhance the efficiency of power management systems and construct smart grids, and it is anticipated to be utilized for the integration of power and communication systems. Full article

This article highlights the development of a platform for monitoring three-phase energy consumption within a university campus. The core of this platform is low-cost IoT energy sensors, which are designed to transmit real-time data to the data center’s server through different IoT communication technologies, enhancing the preexisting electrical measurement network. The newly recommended measurement structure enables the electrical consumption data collection required for analyzing patterns and proposing forecast models to optimize electricity usage. The major contribution of this work is the design and implementation of smart three-phase energy meters based on the selection of various energy sensors and wireless communication technologies, and then the set up of a global IoT architecture that offers real-time data acquisition, storage, download, and visualization, capitalizing on the campus’s diverse energy profiles for detailed characterization. The proposed platform is considered the cornerstone toward the implementation of a collaborative smart microgrid, allowing forecasting and electrical consumption optimization, enabling research into potential opportunities for energy efficiency in our campus, and enhancing the performance of existing electrical infrastructure. Full article

Recent advancements in large language models (LLMs) have added a transformative dimension to the social Internet of Things (SIoT), which is the combination of social networks and IoT. With LLMs’ natural language understanding and data synthesis capabilities, LLMs are regarded as strong tools to enhance SIoT applications such as recommendation, search, and data management. This application-focused review synthesizes the latest related research by identifying both the synergies and the current research gaps at the intersection of LLMs and SIoT, as well as the evolutionary road from machine learning-based solutions to LLM-enhanced ones. Full article

In this study, a Multi-Sensor IoT Device (MSID) is developed that is designed to collect various environmental data and interconnect with the cloud and blockchain to ensure reliable data management. The MSID is designed with a flexible, modular structure that supports a variety of sensor configurations and is easily expandable with 3D-printed components. The system performance was monitored in real-time, with a high cloud upload success rate of 98.35% and an average transmission delay of only 0.64 s, confirming stable data collection every minute. Blockchain-based sensor data storage ensured data integrity and tamper-proofness, with all transactions successfully recorded and verified via smart contract. The proposed Blockchain-based Mobile IoT System (BMIS) has shown strong potential for use in environmental monitoring, industrial asset management, and other areas that require reliable data collection and long-term preservation. Full article

Integrating smart devices from the Internet of Things (IoT) with Customer Relationship Management (CRM) systems presents significant opportunities for enhancing customer experience through real-time data utilization. This article explores the technological frameworks and practical solutions for achieving seamless integration of IoT data within CRM platforms. By leveraging distributed Web systems, this study demonstrates how companies can improve scalability, responsiveness, and personalization in managing customer relationships. This paper outlines key architectural designs for distributed Web systems that ensure efficient real-time data processing while addressing challenges such as security, system integration, and the demands of analytics. This research provides insights into overcoming these challenges with strategies like load balancing, edge processing, and advanced encryption protocols. Results from simulations and practical implementations underscore the effectiveness of these approaches in optimizing operational efficiency and delivering hyper-personalized customer experiences. This study aims to bridge the gap between theoretical possibilities and real-world applications, offering actionable guidelines for organizations to fully leverage IoT-driven CRM systems. Full article

The rapid proliferation of Internet of Things (IoT) devices in healthcare, from wearable sensors to implantable medical devices, has revolutionised patient monitoring, personalised treatment, and remote care delivery. However, the resource-constrained nature of IoT devices, coupled with the sensitivity of medical data, presents critical security challenges. Traditional encryption methods, while robust, are computationally intensive and unsuitable for IoT environments, leaving sensitive patient information vulnerable to cyber threats. Addressing this gap, lightweight encryption methods have emerged as a pivotal solution to balance security with the limited processing power, memory, and energy resources of IoT devices. This paper explores lightweight encryption methods tailored for IoT healthcare applications, evaluating their effectiveness in securing sensitive data while operating under resource constraints. A comparative analysis is conducted on encryption techniques such as AES-128, LEA, Ascon, GIFT, HIGHT, PRINCE, and RC5-32/12/16, based on key performance metrics including block size, key size, encryption and decryption speeds, throughput, and security levels. The findings highlight that AES-128, LEA, ASCON, and GIFT are best suited for high-sensitivity healthcare data due to their strong security features, while HIGHT and PRINCE provide balanced protection for medium-sensitivity applications. RC5-32/12/16, on the other hand, prioritises efficiency over comprehensive security, making it suitable for low-risk scenarios where computational overhead must be minimised. The paper underscores the significant trade-offs between efficiency, security, and resource consumption, emphasising the need for careful selection of encryption methods based on the specific requirements of IoT healthcare environments. Additionally, the paper highlights the growing demand for lightweight encryption methods that balance energy efficiency with robust protection against cyber threats. These insights offer valuable guidance for researchers and practitioners seeking to enhance the security of IoT-based healthcare systems while ensuring optimal performance in resource-constrained settings. Full article

The Manufacturing Message Specification (MMS) protocol is frequently used to automate processes in IEC 61850-based substations and smart-grid systems. However, it may be susceptible to a variety of cyber-attacks. A frequently used protection strategy is to deploy intrusion detection systems to monitor network traffic for anomalies. Conventional approaches to detecting anomalies require a large number of labeled samples and are therefore incompatible with high-dimensional time series data. This work proposes an anomaly detection method for high-dimensional sequences based on a bidirectional LSTM autoencoder. Additionally, a text-mining strategy based on a TF-IDF vectorizer and truncated SVD is presented for data preparation and feature extraction. The proposed data representation approach outperformed word embeddings (Doc2Vec) by better preserving critical domain-specific keywords in MMS traffic while reducing the complexity of model training. Unlike embeddings, which attempt to capture semantic relationships that may not exist in structured network protocols, TF-IDF focuses on token frequency and importance, making it more suitable for anomaly detection in MMS communications. To address the limitations of existing approaches that rely on labeled samples, the proposed model learns the properties and patterns of a large number of normal samples in an unsupervised manner. The results demonstrate that the proposed approach can learn potential features from high-dimensional time series data while maintaining a high True Positive Rate. Full article

The objective of this study is to conduct an analysis of the scientific literature on the application of the Internet of Things (IoT) and artificial intelligence (AI) in enhancing supply chain operations. This research applies a dual approach combining bibliometric analysis and topic modeling to explore both quantitative citation trends and qualitative thematic insights. By examining 810 qualified articles, published between 2011 and 2024, this research aims to identify the main topics, key authors, influential sources, and the most-cited articles within the literature. The study addresses critical research questions on the state of IoT and AI integration into supply chains and the role of these technologies in resolving digital supply chain management challenges. The convergence of IoT and AI holds immense potential to redefine supply chain management practices, improving productivity, visibility, and sustainability in interconnected global supply chains. This research not only highlights the continuous evolution of the supply chain field in light of Industry 4.0 technologies—such as machine learning, big data analytics, cloud computing, cyber–physical systems, and 5G networks—but also provides an updated overview of advanced IoT and AI technologies currently applied in supply chain operations, documenting their evolution from rudimentary stages to their current state of advancement. Full article