Over the past few years, there has been an undeniable surge in the deployment of IoT devices. However, this rapid growth has brought new challenges in cybersecurity, as unauthorized device deployment, malicious code modification, malware deployment, and vulnerability exploitation have emerged as significant issues. As a result, there is a growing need for device identification mechanisms based on behavior monitoring. To address these challenges, Machine Learning (ML) and Deep Learning (DL) techniques have been increasingly employed due to advances in the field and improved processing capabilities. However, cyber attackers have developed adversarial attacks that focus on modifying contexts and evading ML evaluations applied to IoT device identification solutions. This article highlights the importance of addressing cybersecurity challenges in the IoT landscape and proposes a hardware behavior-based individual device identification approach using an LSTM-MLP architecture. The proposed architecture was compared to the most common ML/DL classification techniques using data collected from 45 Raspberry Pi devices running identical software and showing promising results in improving device identification. The proposed LSTM-MLP method outperformed previous solutions, achieving an average increase in F1-Score of +0.97 and a minimum TPR of 0.97 for all devices.

Impedance biosensing offers a highly sensitive and non-invasive method for detecting biomolecules and monitoring cellular activities, which is crucial for timely diagnosis and management of viral infections. Traditional methods, although effective, often involve costly and cumbersome equipment and require frequent hospital visits, making them less practical for continuous monitoring. This study introduces a novel biosensor and healthcare monitoring system designed to detect viruses through impedance changes caused by the interaction of antibodies and antigens. Utilizing COMSOL/MATLAB simulations, this research accurately models the sensor’s response to electrode functionalization with antibodies, and evaluates how nanoscale adjustments in electrode size and spacing can enhance biosensing capabilities. The proposed system promises continuous patient monitoring, alerting healthcare providers to critical changes that might indicate viral infections or significant shifts in cellular behavior. The performance of the sensor, validated through detailed simulations, demonstrates its potential as an effective tool for healthcare, ensuring timely interventions and improved patient outcomes. The proposed sensor design achieved an accuracy of approximately 92%, a sensitivity of about 85%, and a specificity of roughly 99%, demonstrating its high effectiveness in detecting viral infections and ensuring accurate monitoring. The sensor highlighted its potential as an effective tool for real-time, non-invasive healthcare monitoring.

Partial discharge (PD) classification is essential for the reliable monitoring and maintenance of high-voltage insulation systems. Traditional classifiers based solely on either Phase-Resolved PD (PRPD) images or raw time-domain current pulses are limited in accuracy, particularly under noise contamination, as they fail to jointly exploit spatial and temporal discharge features. To address these challenges, this paper proposes a multimodal Deep-Learning (DL) framework that fuses convolutional neural network (CNN) features extracted from PRPD maps with long short-term memory (LSTM) representations of synchronized High-Frequency Current Transformer (HFCT) waveforms. The fused architecture integrates spatial morphology with pulse dynamics through lightweight fully connected layers. A laboratory dataset of 840 labeled events from 15 kV cross-linked polyethylene (XLPE) cables—including corona, internal, surface, and noise signals—was used for training and validation (70/15/15 split, targeted augmentation, z-score normalization, five-fold cross-validation). The fused CNN–LSTM achieved 96.3% accuracy, 94.8% recall, and a 95.5% F1-score, outperforming CNN-only (92.4%), LSTM-only (90.1%), and parallel fusion (94.9%) baselines. The ~2.1M-parameter model was deployed and profiled on an NVIDIA Jetson TX2. Embedded inference on Jetson TX2 completes in ≈15 ms per sample (FP16, batch = 1), satisfying within-cycle operation for 50 Hz systems (20 ms per cycle); half-cycle (≈10 ms) targets are feasible with INT8 quantization/pruning. By jointly modeling PRPD spatial patterns and temporal waveform characteristics, the proposed approach substantially enhances PD diagnostic reliability and robustness for intelligent condition monitoring of medium-voltage power assets.

Impedance-based biosensing has emerged as a critical technology for high-sensitivity biomolecular detection, yet traditional approaches often rely on bulky, costly impedance analyzers, limiting their portability and usability in point-of-care applications. Addressing these limitations, this paper proposes an advanced biosensing system integrating a Silicon Nanowire Field-Effect Transistor (SiNW-FET) biosensor with a high-gain amplification circuit and a 1D Convolutional Neural Network (CNN) implemented on FPGA hardware. This attempt combines SiNW-FET biosensing technology with FPGA-implemented deep learning noise reduction, creating a compact system capable of real-time viral detection with minimal computational latency. The integration of a 1D CNN model on FPGA hardware for adaptive, non-linear noise filtering sets this design apart from conventional filtering approaches by achieving high accuracy and low power consumption in a portable format. This integration of SiNW-FET with FPGA-based CNN noise reduction offers a unique approach, as prior noise reduction techniques for biosensors typically rely on linear filtering or digital smoothing, which lack adaptive capabilities for complex, non-linear noise patterns. By introducing the 1D CNN on FPGA, this architecture enables real-time, high-fidelity noise reduction, preserving critical signal characteristics without compromising processing speed. Notably, the findings presented in this work are based exclusively on comprehensive simulations using COMSOL and MATLAB, as no physical prototypes or biomarker detection experiments were conducted. The SiNW-FET biosensor, functionalized with antibodies specific to viral antigens, detects impedance shifts caused by antibody–antigen interactions, providing a highly sensitive platform for viral detection. A high-gain folded-cascade amplifier enhances the Signal-to-Noise Ratio (SNR) to approximately 70 dB, verified through COMSOL and MATLAB simulations. Additionally, a 1D CNN model is employed for adaptive noise reduction, filtering out non-linear noise patterns and achieving an approximate 75% noise reduction across a broad frequency range. The CNN model, implemented on an Altera DE2 FPGA, enables high-throughput, low-latency signal processing, making the system viable for real-time applications. Performance evaluations confirmed the proposed system’s capability to enhance the SNR significantly while maintaining a compact and energy-efficient design suitable for portable diagnostics. This integrated architecture thus provides a powerful solution for high-precision, real-time viral detection, and continuous health monitoring, advancing the role of biosensors in accessible point-of-care diagnostics.