Federated learning (FL) enables decentralized model training without sharing raw data, but its use in wireless sensor networks (WSNs) for natural disaster management remains underexplored. In this paper, we address this gap by proposing a data-aware clustered FL system tailored for disaster scenarios. We introduce the Data-Aware Disk Covering Problem (DA-DCP), a clustering method that leverages central knowledge of data distributions to form balanced clusters. These clusters serve as FL agents, improving both clustering efficiency and model convergence under heterogeneous data conditions. The simulation results highlight the advantages of DA-DCP in accelerating learning and improving robustness for disaster response.

The integrity of Internet of Things (IoT) devices has caused a fast spread in an era of data-driven decision-making across businesses. This tutorial survey provides a comprehensive review of current IoT data handling advances, focusing on data quality management (DQM). The article starts with the key aspects of IoT data management. In this regard, we shed light on the data source, volume and velocity, variety, lifecycle, security and privacy, scalability and distribution processing, anomaly detection, and energy efficiency. Then, We present a comprehensive taxonomy of IoT DQM based on the application type, such as smart cities, healthcare, agriculture, environmental monitoring, retail and supply chain, and smart grids (SGs). As IoT data processing, analysis, and security play a significant role in DQM; this tutorial survey carefully addresses how modern technologies maintain this role. More particularly, this work investigates the use of edge computing for real-time data processing and the incorporation of synthetic data to supplement restricted resources incorporating the issues of managing the massive datasets created by IoT implementations. In addition, the paper addresses the use of machine learning (ML) algorithms for in-depth analysis of IoT data streams, DQ evaluation protocols, and detection tactics during data transfer. Moreover, the article investigates complete security measures for protecting sensitive data, such as access control regulations and several security techniques, including authentication, encryption, and secure communication protocols that enable IoT data management. Besides, blockchain technology’s significant roles in this regard have been comprehensively addressed. Along with summarizing and reviewing the latest efforts in DQM in IoT-based systems, we shed light on their strong and weak points and discuss upcoming trends and potential difficulties in IoT data management. Last but not least, we continue by emphasizing the cumulative impact of these advances and shedding light on the open issues and challenges. Finally, this in-depth tutorial survey aims to be a significant resource for academics, practitioners, and stakeholders interested in the changing environment of IoT data management, with a particular emphasis on DQ.

Federated Learning (FL) is a machine learning (ML) approach that allows a model to be trained across multiple decentralized devices holding local data samples without exchanging them. In the realm of Wireless Sensor Networks (WSNs), FL has not attracted much attention given that FL is typically meant to train models on data collected by much fewer and decently more powerful devices. However, given the potential of WSNs to collect diverse data in hazardous regions, we aim to explore how to employ FL to collect data in an area of interest where we have a natural disaster. In this paper, we introduce a novel task with regards to FL in the context of WSN for natural disaster management. Given a region where wireless sensors are deployed and data samples are distributed, we aim to cluster the sensors so that each cluster can be treated as a FL agent in a way that accelerates the process of FL.

The effects of explosions and other manmade seismic sources pose a threat to humanity. One of the most pressing issues currently confronting seismologists is contamination of seismicity catalogs. In order to distinguish tectonic from non-tectonic occurrences, an automated control system must be developed, and since detecting quarry blasts (QBs) is the initial and always tough stage, this is an absolute necessity. The need to locate and eliminate the man-made seismic disturbances has increased dramatically. In order to aid in precise seismic hazard identification and improve the planning of future urban developments, early treatments and cleaning of contaminated seismicity catalogs are necessary. Machine learning (ML) methods have allowed for greater precision in identifying synthetic seismic sources. Distinguishing between QBs and natural earthquakes is currently the focus of numerous methodologies, ML techniques, and varied processes, such as knowledge discovery. In order for intelligent systems to learn from repeated encounters and spot and identify patterns in a dataset, ML techniques provide a variety of probabilistic and statistical methods. The purpose of this research is to develop an algorithm that can identify QBs inside seismicity databases automatically. To be more specific, we use classical and ensemble ML classifiers to categorize reports of seismic activity. In order to improve performance, the suggested technique makes use only three features (Latitude, Longitude, and Magnitude). The accuracy of the proposed scheme is examined by R2, F1-score, MCC score, kappa score, elapsed time, learning curve, and confusion matrix. The proposed mode has demonstrated the superior performance as compared to the benchmarks with a testing accuracy of 97.21 %.

River floods stand among the natural disasters with far-reaching impacts, affecting human lives, the economy, infrastructure, agriculture, and more. Substantial investments by organizations are directed toward innovative strategies for flood prevention. The concept of Artificial Intelligence of Things (AIoT), a fusion of Artificial Intelligence and Internet of Things technologies, has showcased its prowess across various domains. In this paper, we introduce an AIoT framework where river flood sensors, located in every region, transmit their data using LoRaWAN technology to local broadcast centers in proximity. These broadcast centers subsequently forward the data via 4G/5G networks to a centralized cloud server. The server employs efficient AI algorithms to analyze the data and predict river conditions nationwide, contributing to proactive flood prevention. This approach has demonstrated effectiveness on multiple fronts. LoRaWAN-based communication between sensor nodes and broadcast centers offers reduced energy consumption and expanded coverage, while AI-driven data analysis enhances the accuracy of river flood predictions.

The safeguarding and security of sensitive data face considerable obstacles in the face of natural disasters, as there exists the possibility of data loss or illegal access. This research study examines various tactics for protecting sensitive data in the event of natural disasters. These strategies include data backup and recovery, data encryption, cloud-based solutions, physical protection measures, and the implementation of disaster recovery plans. Through a thorough examination of various methodologies, this study offers valuable perspectives on practical strategies for safeguarding confidential information. This enables both individuals and businesses to effectively manage potential risks and maintain the integrity of their data, particularly in the context of natural catastrophes. The research places significant emphasis on the necessity of consistent data backup, delves into encryption methods for data both at rest and in transit, analyzes the advantages and obstacles associated with safeguarding data through cloud-based mechanisms, scrutinizes physical security measures implemented in data centers, and underscores the importance of comprehensive disaster recovery strategies. This study paper offers valuable insights on how to improve data security policies, thereby enabling the efficient safeguarding of critical data during natural catastrophes.

Natural disasters pose significant challenges to disaster management agencies, necessitating the development of efficient solutions to reduce risks and mitigate the impact on affected communities. This paper aims to contribute to the improvement of response planning, decision-making, and resource allocation in natural disaster management by conducting a comprehensive analysis of the utilization of formal approaches. The paper explores the advantages and disadvantages of various formal modeling techniques employed in disaster management. Mathematical modeling, for instance, enables the representation and analysis of complex systems, allowing decision-makers to gain insights into the dynamics of disaster scenarios. Simulation techniques provide a means to assess the performance and effectiveness of response strategies, facilitating evidence-based decision-making. Verification methods ensure the correctness and reliability of disaster management systems, reducing the chances of errors and improving their effectiveness. Moreover, the study investigates the potential benefits of integrating formal methodologies with emerging technologies such as machine learning and data analytics. By combining formal methods with these advanced technologies, disaster management systems can leverage the power of data-driven insights for improved decision-making and resource allocation. Machine learning algorithms can analyze large volumes of data to identify patterns and correlations, enabling proactive measures and more accurate predictions. Data analytics techniques can extract valuable information from diverse data sources, supporting the optimization of resource allocation and response strategies. The ultimate goal of this study is to provide a valuable resource for researchers and practitioners interested in the application of formal methods to the complex and challenging problem of managing natural disasters. By offering a detailed analysis of the advantages, limitations, and potential integration with emerging technologies, this paper aims to enhance the understanding and adoption of formal approaches in disaster management. It is our hope that this study will contribute to the development of more efficient and effective strategies for mitigating the impact of natural disasters and protecting vulnerable communities.

This article delves at the potential of artificial intelligence (AI) and drone-based technologies for disaster relief. Potential applications of these technologies in disaster response are discussed; they include the use of drones to survey the scene and look for survivors, and the use of AI-based systems to offer real-time data to rescue workers. We discuss the future directions and research directions for AI and drone-based disaster management, including the integration of AI and drone-based technologies, the development of multi-agent systems, and the importance of explainable AI and ethical considerations. Finally, we end by stressing the need to advance AI and drone-based technologies for use in disaster management and their potential to lessen the global effect of natural disasters.

6G-based wireless communication system is poised to redefine the next-generation network landscape by enabling novel services and applications, such as intelligent link establishment, power control, data collection, transmission, and distribution. However, security issues, particularly recently revealed channel access attack (CAA), present significant challenges to performance optimization tasks in the heterogeneous wireless networks of 6G, namely, Age of Information (AoI) oriented Network (AoN), Throughput oriented Network (ToN), and Latency oriented Network (LoN). To address these challenges, this article presents a game theory-based smart optimization solution to enable unmanned aerial vehicles (UAV) to resist CAA within a 6G-based heterogeneous network. Our methodology begins by outlining the advantages and challenges associated with UAV usage, followed by the design of performance indicators and intelligent resource allocation schemes under the influence of CAA. Subsequently, we introduce definitions and categories within game theory, encompassing the concept and equilibrium of three typical game models. The efficacy of our proposed framework is validated through simulation results, which demonstrate the achievement of optimal AoI, enhanced throughput, and reduced latency compared with baseline methodologies when countering CAA in a UAV-assisted heterogeneous network.

Smart contracts are digital contracts that rely on Blockchain technology to make their terms and execution conditions unforgeable. The purpose of a smart contract is to eliminate the need for a middleman in business and trade between anonymous and identified participants. Since 2016, smart contracts have been gaining traction in various areas, including public management, supply chain, energy, finance, communication, and healthcare. Anyone who interacts with a smart contract after it is launched on the blockchain system will be in danger if it contains vulnerabilities or faults. Therefore, the use of formal methods which are mathematical techniques for modeling, designing, and testing software and hardware systems to ensure they are constructed correctly, is highly required. In this paper, the applied state-of-the-art formal methods on smart contracts specification and verification have been reviewed with the aim of minimizing the risk of faults and bugs occurrence and avoiding possible resulting costs. Also, we have discussed several challenges and future research guidelines related to this emerging research tonic.

Summary In this study, we tackle the problem of author profiling. The aim of the proposed approach is to determine the author's age and gender. Once the user connects to the company website, this company collects the available data about him (which is usually very limited). Then, the user receives a service recommendation according to his gender and age. Thus, a context‐specific decision‐making system based on these limited data is required to produce an efficient classification. Such a decision system allows companies to promote their marketing. To obtain the best categorization, machine learning (ML) and deep learning (DL) techniques have been applied in the literature. In this article, we apply both classical ML techniques and recently developed DL techniques. More precisely, we adopt the gated recurrent unit model. Our experiments show that our findings are positively comparable with the best state‐of‐the‐art methods.

International audience

Recent research focus more and more on IoT systems and their applications in order to make people life easier and controllable. The main aim is to expand IoT applications and services into various domains while ensuring communication and automated exchange between them. Recent research handles many issues related to IoT especially implementation, modeling, and deployment. However, many challenges need more deep and thorough analysis especially in terms of flexible modeling, extensible implementation, with respect to the privacy issue. This work focuses principally on modeling IoT systems dedicated to smart healthcare case. We attempt to address the emergency service by initiating a modeling mechanism for Healthcare Management System (HMS) by using UML diagrams, and propose an appropriate access control in order to reinforce it. Then, we ensure the correctness of the developed HMS by relying on the verification and validation based on a formal analysis that showed significant results by using Alloy tool.

The goal of this work is to make a contribution to the development of computationally efficient multirate Electrocardiogram (ECG) automated detectors of arrhythmia. It utilizes an intelligent combination of multirate denoising plus wavelet decomposition for an effective realization of the ECG wireless implants. The decomposed signal subband features are mined and in next step these are utilized by the mature k-Nearest Neighbor (KNN) classifier for arrhythmia diagnosis. The multirate nature substantially reduces the processing activity of the system and thus allows a dramatic decrease in energy consumption compared to traditional counterparts. The performance of the system is estimated also in terms of the classification performance. Obtained results reveal an overall 22.5-fold compression gain and 4-folds processing outperformance over the traditional equals while securing 93.2% highest classification accuracy and specificity of 0.956. Findings confirm that the proposed solution could potentially be embedded in contemporary automatic and mobile cardiac diseases diagnosis systems.

In most cities, the availability of parking is a major concern. The misuse of parking spots as drivers park for longer than permitted periods cause more delays, inconvenience to others, and even parking tickets. Moreover, the payment systems at many locations are still not electronic and rely on hard currency. The search for a parking space also contributes to congestion, pollution, and other safety issues. This paper introduces an end-to-end system that enables automatic car payments in a safe, private, secure, and efficient manner using Blockchain technology. The proposed solution utilizes Ethereum to prototype a solution which can facilitate the parking payments. In addition, Android auto and application modules that automate the payment process have also been developed. Moreover, a validation technique for enhancing the quality and correctness of the proposed solution, namely Model-Based Testing Techniques, has been discussed. The latter consists of deriving test suites from an adopted formal model, performing them, and assessing the correctness. The used formal model may combine both functional and load aspects. A list of techniques for improving the formal testing approach was identified. Besides, the authors explained how to manage dynamic adaptations of the system under test and how to use isolation strategies for avoiding interference between testing and business behaviors. Finally, an optimization phase for testers placement inspired by fog computing is proposed as well.

Cybersecurity attacks are exponentially increasing, making existing detection mechanisms insufficient and enhancing the necessity to design more relevant prediction models and approaches. This issue is still an open research problem since existing attack prediction models are failing to follow the huge amount of attacks and their variety. Recently, machine learning approaches and especially deep learning techniques have received much attention from researchers since their unparalleled high performance in several prediction-based fields. In this context, this paper explores the application of deep learning techniques for predicting cybersecurity attacks. Particularly, it proposes a new LSTM (Long Short-Term Memory), RNN (Recurrent Neural Network), and MLP (Multilayer Perceptron) based models carefully designed to predict the type of attack potentially to hap-pen. The proposed models were validated using a recently available dataset called CTF showing encouraging results especially for the LSTM model with an f-measure greater than 93%.

In this article we are interested in optimizing the placement problem of security testing components for Internet of Things Architectures. Our goal is to extend existing techniques used in Fog computing to distribute application components over computational nodes. For that purpose, we identify several types of constraints, objectives functions and algorithms that can be adopted.

International audience

Web services compositions are still considered as a major player in the implementation of distributed architectures. Such applications must provide services to hundreds of users simultaneously. In this context, load testing of these applications seems an important task in order to detect problems under elevated loads. For this purpose, we proposed a distributed test architecture aiming to study the behavior of WS-BPEL compositions considering load conditions. The developed test approach is performed based on two steps. The first one is to run a load test during which the composition under test is monitored and performance data are recorded. The second step is to analyze the resulting test logs in order to identify problems under load. For that, we proposed a classification of these problems according to both their natures and causes. Finally, we concretized our solution by implementing a testing tool (WSCLim) and we evaluated it in the context of a Travel Agency case study.

We propose in this paper a new approach for conformance testing of WS-BPEL compositions under various load conditions. It is based on Timed Automata as model for testing WS-BPEL implementations, a distributed testing framework that automatically generates and executes parallel tests online, and an algorithm for online test generation and execution. We also implemented a part of our solution in the form of a prototype tool named WSCCT for WS-BPEL compositions conformance testing.