The monitoring and detection of wild animals is a significant topic for researchers who study the behavior, lifestyle, and environment of wild animals, as well as for people who encounter wildlife both in residential areas and near roads while traveling. An innovative wild-animal detection internet-of-things (IoT) sensor network running on harvested solar energy and detection methodology is described in this article. The sensor-networks node is implemented via the principle of an embedded system incorporating passive infrared sensors, a long-range (LoRa) module, and a solar panel for energy harvesting. For experimental purposes, a small IoT sensor network was implemented near the road. The network consists of eight nodes placed near the road with a distance of 50 m between nodes, a gateway for gathering detection data from the nodes, and a thermo-vision camera for verification of the received data.

This paper investigates the critical aspect of synchronization in wireless sensor networks (WSNs) across diverse industrial applications. The low-cost sensor network topologies are analyzed. The communication delay measurements and quantitative jitter analysis are performed under different conditions, and dependencies of the propagation time delay on the data bitrate and modulation type for different hardware implementations of the WSNs are presented. The time delay distribution influence on the time synchronization error propagation over WSN layers was assessed from the experimental probability density functions. The network synchronization based on the controlled propagation delay jitter approach has been proposed. This research contributes quantitative insights into the complexities of synchronization in WSNs, offering a foundation for optimizing network configurations and parameters to extend the operational life of low-power sensor nodes.

A smart capacitive transducer (SCT) for high-frequency vibration (HFV) measurements was developed, featuring self-calibration for the improvement of measurement accuracy. Measurements using this transducer are performed by positioning it over a thin (10 µm) dielectric layer on a conductive surface. This method was shown to be a non-contact vibration measurement technique for solid surfaces at frequencies over 10 kHz. Auto-calibration is performed every time the SCT is placed on the object being measured. This reduces the influence of positioning and the object’s surface properties on the measurement results. For the transducer’s auto-calibration, a predefined vibration of the measurement electrode is induced. This is achieved using a waveguide excited by a piezo element. The diameter of the developed SCT is 5 mm, with a frequency range of 10 kHz to 1 MHz, an object HFV amplitude measurement resolution of several picometers, and a repeatability error of several percent.

In this paper, the near-field radiated susceptibility pre-mapping method is proposed using the improved near-field probe power radiation profile assessment. The modelling of the electromagnetic field strength in 80–3000 MHz range in the proximity of the near-field probe was performed. The −6 dB aperture boundaries of the near-field probe and their variation, due to the proximity of the radio frequency (RF) printed circuit board (PCB) components, were determined, while the aperture map distortion, arising from the proximity of the passive RF PCB components were evaluated. The scanning path requirements for the RF susceptibility mapping were determined. The simulation of improved near-field probe absolute magnetic field strength reference map in open-air conditions is carried out in this work. The comparative analysis using the absolute maximum difference metric of orthogonal absolute magnetic field map cross-sections between the reference map and magnetic field maps affected by the proximity of the components was carried out. The experimental study of the RF amplifier stage susceptibility map with susceptibility mapping measurement results are presented in this work.

The study presents a comparative analysis of five distinct image processing methodologies for roadside wild animal detection using thermal imagery, aiming to identify an optimal approach for embedded system implementation to mitigate wildlife–vehicle collisions. The evaluated techniques included the following: bilateral filtering followed by thresholding and SIFT feature matching; Gaussian filtering combined with Canny edge detection and contour analysis; color quantization via the nearest average algorithm followed by contour identification; motion detection based on absolute inter-frame differencing, object dilation, thresholding, and contour comparison; and animal detection based on a YOLOv8n neural network. These algorithms were applied to sequential thermal images captured by a custom roadside surveillance system incorporating a thermal camera and a Raspberry Pi processing unit. Performance evaluation utilized a dataset of consecutive frames, assessing average execution time, sensitivity, specificity, and accuracy. The results revealed performance trade-offs: the motion detection method achieved the highest sensitivity (92.31%) and overall accuracy (87.50%), critical for minimizing missed detections, despite exhibiting the near lowest specificity (66.67%) and a moderate execution time (0.126 s) compared to the fastest bilateral filter approach (0.093 s) and the high-specificity Canny edge method (90.00%). Consequently, considering the paramount importance of detection reliability (sensitivity and accuracy) in this application, the motion-based methodology was selected for further development and implementation within the target embedded system framework. Subsequent testing on diverse datasets validated its general robustness while highlighting potential performance variations depending on dataset characteristics, particularly the duration of animal presence within the monitored frame.

The increasing prevalence of work-related stress requires advanced, non-intrusive physiological monitoring solutions. As conventional methods are often impractical for continuous, real-world applications, this study investigates the deployment of artificial intelligence models on embedded systems for real-time emotion recognition from physiological signals. The study identified critical constraints for embedded implementation, including model size and memory capacity. An evaluation of various machine learning algorithms revealed that, while models like K-Nearest Neighbors (KNN) achieve high accuracy (88.8%), their excessive memory footprints make them unsuitable for resource-constrained hardware. Consequently, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and recurrent neural network (RNN) architectures were deployed on an STM32F411 microcontroller, for which model compression proved essential. An experimental study validated the approach, achieving high recognition rates for pronounced emotions such as hatred (91%) and anger (85%), though with a lower accuracy for more subtle states. These results confirm the potential of embedded AI systems for physiological monitoring, highlighting the critical importance of feature selection and model compression for practical implementation.