Advances to IoT security using a GRU-CNN deep learning model trained on SUCMO algorithm

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 12, 2025

The rapid expansion of the Internet Things (IoT) has significantly improved various aspects our daily life. However, along with its benefits, new security threats such as Denial Service (DoS) attacks and Botnets have emerged. To adopt this technology integrity IoT environment, detection become crucial. This paper proposes a hybrid deep learning model that combines Convolutional Neural Network (CNN) Gated Recurrent Units (GRUs) to classify threats. CNN is used extract spatial features from network data, where on other hand GRUs for capturing temporal dependencies. combination makes effective at analysing both static dynamic data. Further, optimize performance proposed model, self-upgraded Cat Mouse Optimization (SUCMO) algorithm employed, state art optimization technique. SUCMO fine-tunes model's hyperparameters improve classification accuracy. evaluated through experiments two different datasets i.e., UNSW-NB15 BoT-IoT, results demonstrates work outperforms traditional well works.

Language: Английский

---

A Flexible Organomagnetic Single-Layer Composite Film with Built-In Multistimuli Responsivity

ACS Applied Materials & Interfaces, Journal Year: 2024, Volume and Issue: 16(44), P. 60686 - 60698

Published: Oct. 28, 2024

Materials possessing multiple properties and functionalities, that can be controlled or modulated by external stimuli, are a central focus of current research in materials sciences due to their potential significantly enhance various future technological applications. Herein, we report significant advancement this field through the development smart, multifunctional organomagnetic composite material. By utilizing thin layer polydimethylsiloxane (PDMS) polypyrrole (PPy) precursors, doped with nickel nanoparticles (NiNPs), have created an innovative organomagnetic, PDMS/PPy/NiNPs (PPN), single-layer film displays multistimuli responsivity. The study presents first demonstration flexible, three-component structure integrating structural flexible PDMS component, together conductive polymer component metal-based into design, which enhanced unprecedented responsivity against different stimuli. Unlike typical stacked multilayered structures, exhibit one two functionalities at most, novel configuration exhibits including magnetoresistance, mechanical stress response, piezoresistivity, temperature change sensitivity. as-prepared demonstrates notable magnetoresistance responsivity, relative electrical resistance, Δ

Language: Английский

---

A strain-sensitive neuromorphic device emulating mechanoreception for different skin sensitivities

Journal of Materials Chemistry C, Journal Year: 2024, Volume and Issue: 12(45), P. 18243 - 18255

Published: Jan. 1, 2024

A strain-sensitive neuromorphic device mimics mechanoreception, adapting to skin-like sensitivities. Embedded Au microwires in PDMS detect strain and display functionalities, closely replicating biological mechanosensory functions.

Language: Английский

---

Fabrication of strain-sensing fibers with silver nanoparticles and reduced graphene oxide via wet spinning

Nanotechnology, Journal Year: 2024, Volume and Issue: 36(10), P. 105501 - 105501

Published: Dec. 24, 2024

To advance the industrialization of flexible strain sensors, an innovative sensing fiber was developed through a sophisticated wet spinning process. Silver trifluoroacetate and graphene oxide (GO) were combined with thermoplastic polyurethane (TPU) to prepare fibers via spinning. Ascorbic acid used

Language: Английский

---