Machine learning and internet of things applications in enterprise architectures: Solutions, challenges, and open issues

Expert Systems, Journal Year: 2023, Volume and Issue: 41(1)

Published: Oct. 18, 2023

Summary The rapid growth of the Internet Things (IoT) has led to its widespread adoption in various industries, enabling enhanced productivity and efficient services. Integrating IoT systems with existing enterprise application become common practice. However, this integration necessitates reevaluating reworking current Enterprise Architecture (EA) models Expert Systems (ES) accommodate cloud technologies. Enterprises must adopt a multifaceted view automate aspects, including operations, data management, technology infrastructure. Machine Learning (ML) is powerful smart automation tool within EA. Despite potential, need for dedicated work focuses on ML applications services systems. With being significant field, analyzing IoT‐generated IoT‐based networks crucial. Many studies have explored how can solve specific IoT‐related challenges. These mutually reinforcing technologies allow leverage sensor model improvement, leading operations practices. Furthermore, techniques empower knowledge enable suspicious activity detection objects. This survey paper conducts comprehensive study role applications, particularly domains security. It provides an in‐depth analysis state‐of‐the‐art approaches context IoT, highlighting their contributions, challenges, potential applications.

Language: Английский

---

Deep learning-driven hybrid model for short-term load forecasting and smart grid information management

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 14, 2024

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, complexity and uncertainty load, along with large-scale high-dimensional energy information, present challenges in handling intricate dynamic features long-term dependencies. This paper proposes a computational approach to address these short-term information management, goal accurately predicting future demand. The study introduces hybrid method that combines multiple deep learning models, Gated Recurrent Unit (GRU) employed capture dependencies time series data, while Temporal Convolutional Network (TCN) efficiently learns patterns data. Additionally, attention mechanism incorporated automatically focus on input components most relevant prediction task, further enhancing model performance. According experimental evaluation conducted four public datasets, including GEFCom2014, proposed algorithm outperforms baseline models various metrics such as accuracy, efficiency, stability. Notably, GEFCom2014 dataset, FLOP reduced by over 48.8%, inference shortened more than 46.7%, MAPE improved 39%. significantly enhances reliability, stability, cost-effectiveness grids, which facilitates risk assessment optimization operational planning under context management grid systems.

Language: Английский

---

Cybersecurity for Sustainable Smart Healthcare: State of the Art, Taxonomy, Mechanisms, and Essential Roles

Deleted Journal, Journal Year: 2024, Volume and Issue: 4(2), P. 20 - 62

Published: May 23, 2024

Cutting-edge technologies have been widely employed in healthcare delivery, resulting transformative advances and promising enhanced patient care, operational efficiency, resource usage. However, the proliferation of networked devices data-driven systems has created new cybersecurity threats that jeopardize integrity, confidentiality, availability critical data. This review paper offers a comprehensive evaluation current state context smart healthcare, presenting structured taxonomy its existing cyber threats, mechanisms essential roles. study explored (SHSs). It identified discussed most pressing attacks SHSs face, including fake base stations, medjacking, Sybil attacks. examined security measures deployed to combat SHSs. These include cryptographic-based techniques, digital watermarking, steganography, many others. Patient data protection, prevention breaches, maintenance SHS integrity are some roles ensuring sustainable healthcare. The long-term viability depends on constant assessment risks harm providers, patients, professionals. aims inform policymakers, practitioners, technology stakeholders about imperatives best practices for fostering secure resilient ecosystem by synthesizing insights from multidisciplinary perspectives, such as cybersecurity, management, sustainability research. Understanding recent is controlling escalating networks encouraging intelligent delivery.

Language: Английский

---

RPL-based attack detection approaches in IoT networks: review and taxonomy

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(9)

Published: Aug. 12, 2024

The Routing Protocol for Low-Power and Lossy Networks (RPL) plays a crucial role in the Internet of Things (IoT) Wireless Sensor Networks. However, ensuring RPL protocol's security is paramount due to its susceptibility various attacks. These attacks disrupt data transmission can substantially damage network topology by depleting critical resources. This paper presents comprehensive survey addressing several key components response this challenge. Firstly, it categorizes potential targeting protocol based on their impact performance explores effective mechanisms secure against them. study identifies most destructive problematic threats affecting functionality. Furthermore, provides valuable insights into challenges discusses real-world implications deploying maintaining IoT sensor networks. To underscore uniqueness survey, we offer qualitative comparison with other surveys same field. While acknowledges certain limitations, such as intentionally focusing only reviewing RPL-specific attacks, reference future researchers seeking comprehend mitigate RPL. It also suggests areas further research domain.

Language: Английский

---

A Survey on Routing Solutions for Low-Power and Lossy Networks: Toward a Reliable Path-Finding Approach

Network, Journal Year: 2024, Volume and Issue: 4(1), P. 1 - 32

Published: Jan. 15, 2024

Low-Power and Lossy Networks (LLNs) have grown rapidly in recent years owing to the increased adoption of Internet Things (IoT) Machine-to-Machine (M2M) applications across various industries, including smart homes, industrial automation, healthcare, cities. Owing characteristics LLNs, such as channels limited power, generic routing solutions designed for non-LLNs may not be adequate terms delivery reliability efficiency. Consequently, a protocol LLNs (RPL) was designed. Several RPL objective functions been proposed enhance LLNs. This paper analyses these against performance security requirements identify their limitations. Firstly, it discusses issues LLN impact on packet Secondly, provides comprehensive analysis identifies existing Thirdly, based limitations, this highlights need reliable efficient path-finding solution

Language: Английский

---

Securing Smart Healthcare Cyber-Physical Systems against Blackhole and Greyhole Attacks Using a Blockchain-Enabled Gini Index Framework

Sensors, Journal Year: 2023, Volume and Issue: 23(23), P. 9372 - 9372

Published: Nov. 23, 2023

The increasing reliance on cyber-physical systems (CPSs) in critical domains such as healthcare, smart grids, and intelligent transportation necessitates robust security measures to protect against cyber threats. Among these threats, blackhole greyhole attacks pose significant risks the availability integrity of CPSs. current detection mitigation approaches often struggle accurately differentiate between legitimate malicious behavior, leading ineffective protection. This paper introduces Gini-index blockchain-based Blackhole/Greyhole RPL (GBG-RPL), a novel technique designed for efficient health monitoring GBG-RPL leverages analytical prowess Gini index advantages blockchain technology sophisticated research not only focuses identifying anomalous activities but also proposes resilient framework that ensures reliability monitored data. achieves notable improvements compared another state-of-the-art referred BCPS-RPL, including 7.18% reduction packet loss ratio, an 11.97% enhancement residual energy utilization, 19.27% decrease consumption. Its features are very effective, boasting 10.65% improvement attack-detection rate 18.88% faster average time. optimizes network management by exhibiting 21.65% message overhead 28.34% end-to-end delay, thus showing its potential enhanced reliability, efficiency, security.

Language: Английский

---

A Fog-Based Privacy-Preserving Federated Learning System for Smart Healthcare Applications

Electronics, Journal Year: 2023, Volume and Issue: 12(19), P. 4074 - 4074

Published: Sept. 28, 2023

During the COVID-19 pandemic, urgency of effective testing strategies had never been more apparent. The fusion Artificial Intelligence (AI) and Machine Learning (ML) models, particularly within medical imaging (e.g., chest X-rays), holds promise in smart healthcare systems. Deep (DL), a subset AI, has exhibited prowess enhancing classification accuracy, crucial aspect expediting diagnosis. However, journey to harness DL’s potential is rife with challenges: notably, intricate landscape data privacy. Striking balance between utilizing patient for insights while upholding privacy formidable. Federated (FL) emerges as solution by enabling collaborative model training across decentralized sources, thus bypassing centralization preserving This study presents tailored, FL architecture screening via X-ray images. Designed facilitate cooperation among institutions, framework ensures remain localized, eliminating need direct sharing. Addressing imbalanced non-identically distributed data, robust solution. Implementation entails localized fog-computing-based models. Localized models utilize Convolutional Neural Networks (CNNs) on institution-specific datasets, model, refined iteratively, takes precedence final classification. Intriguingly, global fortified fog computing, frontrunner after weight refinement, surpassing local Validation COLAB platform gauges model’s performance through metrics such precision, recall, F1-score. Remarkably, proposed excels these metrics, solidifying its efficacy. research navigates confluence FL, imaging, unveiling that could reshape delivery. enriches scientific discourse addressing learning carries implications enhanced care.

Language: Английский

---

Efficient Distributed Denial of Service Attack Detection in Internet of Vehicles Using Gini Index Feature Selection and Federated Learning

Future Internet, Journal Year: 2025, Volume and Issue: 17(1), P. 9 - 9

Published: Jan. 1, 2025

Considering that smart vehicles are becoming interconnected through the Internet of Vehicles, cybersecurity threats like Distributed Denial Service (DDoS) attacks pose a great challenge. Detection methods currently face challenges due to complex and enormous amounts data inherent in IoV systems. This paper presents new approach toward improving DDoS attack detection by using Gini index feature selection Federated Learning during model training. The assists filtering out important features, hence simplifying models for higher accuracy. FL enables decentralized training across many devices while preserving privacy allowing scalability. results show case this is detecting attacks, bringing confidentiality, reducing computational load. As noted paper, average accuracy 91%. Moreover, different types were identified employing our proposed technique. Precisions achieved as follows: DrDoS_DNS: 28.65%, DrDoS_SNMP: 28.94%, DrDoS_UDP: 9.20%, NetBIOS: 20.61%. In research, we foresee potential harvesting from integrating advanced with so systems can meet modern requirements. It also provides robust efficient solution future automotive industry. By carefully selecting only most features decentralizing devices, reduce both time memory usage. makes system much faster lighter on resources, making it perfect real-time applications. Our effective environments.

Language: Английский

---

Ferroresonance Identification by Pattern Recognition of its Characteristic Wavelets

Published: Jan. 1, 2025

Ferroresonance, a non-linear and unpredictable disturbance, is rare compared to traditional power system faults occurring in systems. This rarity, coupled with its complexity, makes it challenging phenomenon be detected identified. work presents detection classification scheme for ferroresonance modes. It carried out by continuously processing the three-phase voltage current signals using discrete wavelet transform (DWT). The developed models are simulated electromagnetic transient software processed DWT extract fault signatures predictors. A decision tree classifier trained detect classify disturbance as an adaptive time based on class. computational burden of process significantly reduced superimposed component inceptions before classification. Furthermore, different modes from other faults, such arcing discussed. timing demonstrates that proposed methodology efficient can into

Language: Английский

---

Intrusion detection in smart grids using artificial intelligence-based ensemble modelling

Cluster Computing, Journal Year: 2025, Volume and Issue: 28(4)

Published: Feb. 25, 2025

Language: Английский

---