An Intelligent Fingerprinting Technique for Low-power Embedded IoT Devices DOI
Varun Kohli, Muhammad Naveed Aman, Biplab Sikdar

et al.

IEEE Transactions on Artificial Intelligence, Journal Year: 2024, Volume and Issue: 5(9), P. 4519 - 4534

Published: April 10, 2024

The Internet of Things (IoT) has been a popular topic for research and development in the past decade. resource-constrained wireless nature IoT devices presents large surface vulnerabilities, traditional network security methods involving complex cryptography are not feasible. Studies show that Denial Service (DoS), physical intrusion, spoofing, node forgery prevalent threats IoT, there is need robust, lightweight device fingerprinting schemes. We identify eight criteria effective propose an intelligent, lightweight, whitelist-based method satisfies these properties. proposed uses power-up Static Random Access Memory (SRAM) stack as fingerprint features Autoencoder Networks (AEN) registration verification. also present threat mitigation framework based on isolation levels to handle potential identified threats. Experiments conducted with heterogeneous pool ten AVR Harvard-architecture prover from different vendors, Dell Latitude XPS 13 laptops used verifier testbeds. 99.9% accuracy, 100% precision, 99.6% recall known unknown devices, which improvement over several works. independence fingerprints stored AENs enables easy distribution update, observed evaluation latency (~ 10 −4 seconds) data collection 1 second) make our practical real-world scenarios. Lastly, we analyze regard highlight its limitations future improvement.

Language: Английский

Analysis of Factors affecting on Energy Consumption: A Case Study of Kolhapur City DOI Open Access
Swati Patil, Mukund Anant Kulkarni, Swati Anil Patil

et al.

Current World Environment, Journal Year: 2025, Volume and Issue: 20(1), P. 513 - 522

Published: May 5, 2025

The impact of many factors on Kolhapur city's energy usage in 2022 will be impartially investigated this study. As urbanization and population growth continue to accelerate Kolhapur, understanding the influencing becomes increasingly critical. city faces challenges related supply, sustainability, environmental impact. Despite growing demand for energy, there is limited research specific that drive consumption Kolhapur. This study aims fill gap by investigating various determinants city.To determine use, a variety data was gathered from Census handbook Maharashtra Electricity Board. findings confirm climate, temperature, growth, time, conditions, pollution, humidity all have statistically significant positive effects usage. Notably, strong correlation between rate, indicating as increases, so does energy. On other hand, cost natural gas water has no effect suggesting are more influential determining patterns.

Language: Английский

Citations

0
The Impact of Social Media Marketing on Online Buying Behavior via the Mediating Role of Customer Perception: Evidence from the Abu Dhabi Retail Industry DOI
Barween Al Kurdi, Mohammed T. Nuseir, Muhammad Turki Alshurideh

et al.

Studies in big data, Journal Year: 2024, Volume and Issue: unknown, P. 431 - 449

Published: Jan. 1, 2024

Language: Английский

Citations

3
Impact of Cyber Security Strategy and Integrated Strategy on E-Logistics Performance: An Empirical Evidence from the UAE Petroleum Industry DOI
Mohammed T. Nuseir,

Enass Khalil Alquqa,

Ata Al Shraah

et al.

Studies in big data, Journal Year: 2024, Volume and Issue: unknown, P. 89 - 108

Published: Jan. 1, 2024

Language: Английский

Citations

3
Boosting wind turbine performance with advanced smart power prediction: Employing a hybrid ARMA-LSTM technique DOI Creative Commons
Abdel‐Haleem Abdel‐Aty, Kottakkaran Sooppy Nisar,

Wedad R. Alharbi

et al.

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 96, P. 58 - 71

Published: April 6, 2024

Wind energy holds significant importance among renewable sources, necessitating precise power forecast systems for the operation of wind turbines. In order to meet urgent requirement accurate forecasting in production, this study introduces a revolutionary Smart Power Prediction System designed especially The suggested approach hybrid model that combines Autoregressive Moving Average (ARMA) and Long Short-Term Memory (LSTM) methods address limitations current strategies capturing both short- long-term dependencies speed data. This combination improves accuracy while successfully mitigating drawbacks conventional methods. To further improve skills, critical temporal frequency domain insights are extracted from data using sophisticated feature extraction techniques, most notably Discrete Wavelet Transform (DWT). With remarkable rate 99.24%, integrated ARMA-LSTM-DWT outperforms by 3.74% after thorough experimentation validation. system's implementation Python highlights its usefulness potential greatly turbine operational efficiency, which will enable improved grid integration management. Finally, developing strong energy-specific system, our work helps create more ecologically friendly sustainable environment.

Language: Английский

Citations

3
An Intelligent Fingerprinting Technique for Low-power Embedded IoT Devices DOI
Varun Kohli, Muhammad Naveed Aman, Biplab Sikdar

et al.

IEEE Transactions on Artificial Intelligence, Journal Year: 2024, Volume and Issue: 5(9), P. 4519 - 4534

Published: April 10, 2024

The Internet of Things (IoT) has been a popular topic for research and development in the past decade. resource-constrained wireless nature IoT devices presents large surface vulnerabilities, traditional network security methods involving complex cryptography are not feasible. Studies show that Denial Service (DoS), physical intrusion, spoofing, node forgery prevalent threats IoT, there is need robust, lightweight device fingerprinting schemes. We identify eight criteria effective propose an intelligent, lightweight, whitelist-based method satisfies these properties. proposed uses power-up Static Random Access Memory (SRAM) stack as fingerprint features Autoencoder Networks (AEN) registration verification. also present threat mitigation framework based on isolation levels to handle potential identified threats. Experiments conducted with heterogeneous pool ten AVR Harvard-architecture prover from different vendors, Dell Latitude XPS 13 laptops used verifier testbeds. 99.9% accuracy, 100% precision, 99.6% recall known unknown devices, which improvement over several works. independence fingerprints stored AENs enables easy distribution update, observed evaluation latency (~ 10 −4 seconds) data collection 1 second) make our practical real-world scenarios. Lastly, we analyze regard highlight its limitations future improvement.

Language: Английский

Citations

3