An EWS-LSTM-Based Deep Learning Early Warning System for Industrial Machine Fault Prediction DOI Creative Commons
Fabio Cassano, Anna Maria Crespino, Mariangela Lazoi

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(7), P. 4013 - 4013

Published: April 5, 2025

Early warning systems (EWSs) are crucial for optimising predictive maintenance strategies, especially in the industrial sector, where machine failures often cause significant downtime and economic losses. This research details creation evaluation of an EWS that incorporates deep learning methods, particularly using Long Short-Term Memory (LSTM) networks enhanced with attention layers to predict critical faults. The proposed system is designed process time-series data collected from printing machine’s embosser component, identifying error patterns could lead operational disruptions. dataset was preprocessed through feature selection, normalisation, transformation. A multi-model classification strategy adopted, each LSTM-based model trained detect a specific class frequent errors. Experimental results show can failure events up 10 time units advance, best-performing achieving AUROC 0.93 recall above 90%. Results indicate approach successfully predicts events, demonstrating potential EWSs powered by enhancing strategies. By integrating artificial intelligence real-time monitoring, this study highlights how intelligent improve efficiency, reduce unplanned downtime, optimise operations.

Language: Английский

Managing natural disasters: An analysis of technological advancements, opportunities, and challenges DOI Creative Commons
Moez Krichen, Mohamed S. Abdalzaher, Mohamed Elwekeil

et al.

Internet of Things and Cyber-Physical Systems, Journal Year: 2023, Volume and Issue: 4, P. 99 - 109

Published: Sept. 30, 2023

Natural disasters (NDs) have always been a major threat to human lives and infrastructure, causing immense damage loss. In recent years, the increasing frequency severity of natural highlighted need for more effective efficient disaster management strategies. this context, use technology has emerged as promising solution. survey paper, we explore employment technologies in order relieve impacts various disasters. We provide an overview how different such Remote Sensing, Radars Satellite Imaging, internet-of-things (IoT), Smartphones, Social Media can be utilized NDs. By utilizing these technologies, predict, respond, recover from NDs effectively, potentially saving minimizing infrastructure damage. The paper also highlights potential benefits, limitations, challenges associated with implementation purposes. While significantly improve NDM, there are that addressed, cost specialized knowledge skills. Overall, provides comprehensive managing sheds light on important role play NDM. exploring applications aims contribute development sustainable

Language: Английский

Citations

60
Digital post-disaster risk management twinning: A review and improved conceptual framework DOI Creative Commons
Umut Lagap, Saman Ghaffarian

International Journal of Disaster Risk Reduction, Journal Year: 2024, Volume and Issue: 110, P. 104629 - 104629

Published: June 24, 2024

Digital Twins (DT) is the real-time virtual representation of systems, communities, cities, or even human beings with substantial potential to revolutionize post-disaster risk management efforts and achieve resilient communities against adverse effects disasters. However, this remains largely unrecognized poorly understood in disaster management. This study explores current achievements, existing challenges, untapped DT management, accordingly, proposes an improved twin-based framework. paper employs a systematic literature review approach focusing on digital twinning (DPRMT) derived from two databases: Scopus Web Science. After screening process exclusion criteria, final analysis synthesizes findings selected set 96 papers. The results revealed that previous studies are not beyond only providing general statements about DT. There need for diverse data collection methods, considering demographic financial aspects, understanding social dynamics, employing dynamic models, recognizing interconnected giving due attention often-neglected recovery phase. comprehensive DPRMT concept framework leveraging decision-makers holistic efficient offers real-time, detailed, data-driven modeling solutions insights into disaster-affected areas communities. It also helpful optimize response planning, resource allocation, scenario testing by capturing complex behaviors systems entities often overlooked studies.

Language: Английский

Citations

16
Early Detection of Earthquakes Using IoT and Cloud Infrastructure: A Survey DOI Open Access
Mohamed S. Abdalzaher, Moez Krichen,

Derya Yiltas-Kaplan

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(15), P. 11713 - 11713

Published: July 28, 2023

Earthquake early warning systems (EEWS) are crucial for saving lives in earthquake-prone areas. In this study, we explore the potential of IoT and cloud infrastructure realizing a sustainable EEWS that is capable providing to people coordinating disaster response efforts. To achieve goal, provide an overview fundamental concepts seismic waves associated signal processing. We then present detailed discussion IoT-enabled EEWS, including use networks track actions taken by various organizations gather data, analyze it, send alarms when necessary. Furthermore, taxonomy emerging approaches using facilities, which includes integration advanced technologies such as machine learning (ML) algorithms, distributed computing, edge computing. also elaborate on generic architecture efficient highlight importance considering sustainability design systems. Additionally, discuss role drones management their enhance effectiveness EEWS. summary primary verification validation methods required under consideration. addition contributions mentioned above, study highlights implications earthquake detection management. Our research involved comprehensive survey existing literature infrastructure. conducted thorough analysis facilities findings suggest can significantly improve speed efforts, thereby reducing economic impact earthquakes. Finally, identify gaps domain future directions toward achieving Overall, provides valuable insights into emphasizes designing

Language: Английский

Citations

37
A Survey on Key Management and Authentication Approaches in Smart Metering Systems DOI Creative Commons
Mohamed S. Abdalzaher, Mostafa M. Fouda, Ahmed A. Emran

et al.

Energies, Journal Year: 2023, Volume and Issue: 16(5), P. 2355 - 2355

Published: March 1, 2023

The implementation of the smart grid (SG) and cyber-physical systems (CPS) greatly enhances safety, reliability, efficiency energy production distribution. Smart grids rely on meters (SMs) in converting power (PGs) a reliable way. However, proper operation these needs to protect them against attack attempts unauthorized entities. In this regard, key-management authentication mechanisms can play significant role. paper, we shed light importance mechanisms, clarifying main efforts presented context literature. First, address intelligent attacks affecting SGs. Secondly, terms cryptography are addressed. Thirdly, summarize common proposed techniques with suitable critique showing their pros cons. Fourth, introduce effective paradigms state art. Fifth, two tools for verifying security integrity protocols presented. Sixth, relevant research challenges addressed achieve trusted SMs manipulations entities future vision. Accordingly, survey facilitate exerted by interested researchers regard.

Language: Английский

Citations

36
Seismic Intensity Estimation for Earthquake Early Warning Using Optimized Machine Learning Model DOI
Mohamed S. Abdalzaher,

M. Sami Soliman,

Sherif M. El-Hady

et al.

IEEE Transactions on Geoscience and Remote Sensing, Journal Year: 2023, Volume and Issue: 61, P. 1 - 11

Published: Jan. 1, 2023

The need for an earthquake early-warning system (EEWS) is unavoidable in order to save lives. In terms of managing disasters and achieving effective risk mitigation, the quick identification earthquake's intensity a valuable factor. light this, on-site measurement can be transmitted over Internet Things (IoT) network. this regard, machine learning (ML) strategy based on numerous linear non-linear models proposed study determination after two seconds from P-wave onset. We call model two-second ML model-based (2S-ML-EIOS). utilized dataset INSTANCE observed by number 386 stations Italian national seismic Our has been trained 50,000 occurrences (150 thousand 2s-three-component windows). ability deal with limited features waveform traces leading reliable estimation intensity. suggested 98.59% accuracy rate predicting 2S-ML-EIOS used centralized IoT promptly send alarm, will then instruct affected administration take appropriate action. results are contrasted those traditional manual solution approach, which corresponds ideal mean. Based extreme gradient boosting (XGB) model, achieve best determination, improved performance demonstrates methodology's efficacy EEWS.

Language: Английский

Citations

35
Boosted federated learning based on improved Particle Swarm Optimization for healthcare IoT devices DOI
Essam H. Houssein, Awny Sayed

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 163, P. 107195 - 107195

Published: June 23, 2023

Language: Английский

Citations

22
A survey on essential challenges in relay-aided D2D communication for next-generation cellular networks DOI
Mahmoud M. Salim, Hussein A. Elsayed, Mohamed S. Abdalzaher

et al.

Journal of Network and Computer Applications, Journal Year: 2023, Volume and Issue: 216, P. 103657 - 103657

Published: May 9, 2023

Language: Английский

Citations

21
Review and analysis of recent advances in intelligent network softwarization for the Internet of Things DOI
Mohamed Ali Zormati, Hicham Lakhlef, Sofiane Ouni

et al.

Computer Networks, Journal Year: 2024, Volume and Issue: unknown, P. 110215 - 110215

Published: Jan. 1, 2024

Language: Английский

Citations

8
Employing Machine Learning for Seismic Intensity Estimation Using a Single Station for Earthquake Early Warning DOI Creative Commons
Mohamed S. Abdalzaher,

M. Sami Soliman,

Moez Krichen

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(12), P. 2159 - 2159

Published: June 14, 2024

An earthquake early-warning system (EEWS) is an indispensable tool for mitigating loss of life caused by earthquakes. The ability to rapidly assess the severity crucial effectively managing disasters and implementing successful risk-reduction strategies. In this regard, utilization Internet Things (IoT) network enables real-time transmission on-site intensity measurements. This paper introduces a novel approach based on machine-learning (ML) techniques accurately promptly determine analyzing seismic activity 2 s after onset p-wave. proposed model, referred as 2S1C1S, leverages data from single station component evaluate intensity. dataset employed in study, named “INSTANCE,” comprises Italian National Seismic Network (INSN) via hundreds stations. model has been trained substantial 50,000 instances, which corresponds 150,000 windows each, encompassing 3C. By capturing key features waveform traces, provides reliable estimation intensity, achieving impressive accuracy rate 99.05% forecasting any 2S1C1S can be seamlessly integrated into centralized IoT system, enabling swift alerts relevant authorities prompt response action. Additionally, comprehensive comparison conducted between results obtained method those derived conventional manual solution method, considered benchmark. experimental demonstrate that employing extreme gradient boosting (XGB), surpasses several ML benchmarks determining thus highlighting effectiveness methodology systems (EEWSs).

Language: Английский

Citations

8
The role of artificial intelligence and IoT in prediction of earthquakes: Review DOI Creative Commons
Joshua Pwavodi, Abdullahi Umar Ibrahim, Pwadubashiyi Coston Pwavodi

et al.

Artificial Intelligence in Geosciences, Journal Year: 2024, Volume and Issue: 5, P. 100075 - 100075

Published: Feb. 27, 2024

Earthquakes are classified as one of the most devastating natural disasters that can have catastrophic effects on environment, lives, and properties. Most recent earthquakes magnitudes greater than > M8. Satellite data, global positioning system, interferometry synthetic aperture radar (InSAR), seismometers such microelectromechanical seismometers, ocean bottom distributed acoustic sensing systems all been used to predict with a high degree success. Despite advances in seismic wave recording, storage, analysis, earthquake time, location, magnitude prediction remain difficult. On other hand, new developments artificial intelligence (AI) Internet Things (IoT) shown promising potential deliver more insights predictions. Thus, this article reviewed use AI-driven Models IoT-based technologies for earthquakes, limitations current approaches, open research issues. The review discusses setbacks due insufficient inconsistencies, diversity precursor signals, earth's geophysical composition. Finally, study examines approaches or solutions scientists employ address challenges they face prediction. analysis is based successful application AI IoT fields.

Language: Английский

Citations

7