Many fields of human activity benefit from the ability to create images of obscured objects placed behind walls and to map their displacement in a noninvasive way. Usually, imaging devices like Synthetic Aperture Radars (SARs) and Ground-Penetrating Radars (GPRs) use expensive dedicated electronics which results in prohibitive prices. This paper presents the experimental implementation and the results obtained from an imaging system capable of performing SAR imaging and interferometric displacement mapping of targets located behind walls, as well as 3D GPR imaging using a low-cost general-purpose radar sensor. The proposed solution uses for the RF section of the system a K-band microwave radar sensor module implementing Frequency-Modulated Continuous Wave (FMCW) operation. The low-cost sensor was originally intended for simple presence detection and ranging for domestic applications. The proposed system was tested in several scenarios and proved to operate as intended for a fraction of the cost of a commercial imaging device. In one scenario, it was able to detect and locate a 15 cm-diameter fire-extinguisher located at a distance of 3.5 m from the scanning system and 1.6 m behind a 3 cm-thick MDF (medium-density fiberboard) wall with cm-level accuracy. In a second test, the proposed system was used to perform interferometric displacement measurements, and it was capable of determining the displacement of a metal case with sub-millimeter accuracy. In a third experiment, the system was used to construct a 3D image of the inside of a wood table with cm-level resolution.

Protected wetlands such as deltas, lakes or rivers provide a sanctuary for many endangered species. In order to protect these areas from illegal human interventions, it is necessary to monitor the unauthorized entrance of motor boats. In order to mitigate such an impact, we have developed a network of floating beacons for underwater acoustic monitoring, using LoRa communication modules operating at 433 MHz. Such beacons should be equipped with compact antennas. In this paper, we use a genetic algorithm approach to design the compact, monopole antennas required for the beacons; size constraints would apply not only to the radiating element but also to the ground plane. Although the antenna input is unbalanced, such a small ground plane may yield common mode currents on the antenna feeder, which distort the radiation pattern of the antenna. In order to investigate the effect of the common mode currents, we developed a distance averaging method, while, for characterizing the antenna, we used a single-antenna method. For the experimental validation of the system in real conditions, a continuous monitoring of the lake was carried out. During the monitoring, multiple events generated by incursions of motor boats were successfully detected and recorded.

This study explores the application of the Artificial Intelligence of Things (AIoT) in viticulture for the early detection of grapevine diseases. By integrating Internet of Things (IoT) sensors with machine learning algorithms, the system is designed to detect potential grapevine pathogens in real time. Deployed at the Murfatlar vineyard in Romania, which grows Cabernet Sauvignon and Sauvignon Blanc, the system allows for proactive disease management, thus improving grapevine health and reducing crop losses. IoT sensors are installed in the field to collect real-time data on grapevine health, which is then transmitted to the cloud for storage and analysis. Machine learning (ML) algorithms, running on a server with an NVIDIA R3900 card, process this data to predict potential infections caused by pathogens such as Plasmopara viticola, Uncinula necator, and Botrytis. Cloud computing facilitates data processing and real-time visualization, allowing farmers to make timely, data-driven decisions for disease control. The paper outlines the hardware and software components that constitute the diagnostic system.

In recent years, the concept of the Internet of Things (IoT) has spread in most fields due to the multiple benefits it offers, so it recently started to be used in viticulture, together with artificial intelligence (AI). These two innovative technologies combined with classical methods can lead to a much more efficient and rapid prediction of diseases that may occur in grapevine culture. The present study aims to detect diseases in the period when evolution can still be prevented, by minimizing the favorable environment in which the pathogen can develop. This prevention can be achieved using algorithms for predicting and comparing the data from IoT sensors with the data classically gathered by farmers. The IoT sensors system developed to acquire information about environmental parameters is tested in the Murfatlar vineyard, Romania. Two types of untreated Cabernet and Sauvignon Blanc varieties are used in the experimental study with the aim of reducing the chemical treatment concentration. All the sensors’ data are stored in a cloud. This paper presents an analysis of sensor data consisting of soil parameters such as temperature, humidity, conductivity, nitrogen (N), phosphorus (P), and potassium (K). Big data algorithms using machine learning (ML) for clustering and prediction are tested to identify the vine diseases. The results are detailed at the end of the paper.

Growing traffic demand, congestion and transport-related emissions continue to challenge urban mobility and place increasing pressure on existing road infrastructure. This study investigates how smart traffic lights can improve traffic flow and support more efficient urban traffic management. The proposed architecture integrates radar sensors for vehicle and pedestrian detection and vehicle speed estimation with air quality, temperature and humidity monitoring. The CW (HB100) and FMCW (K-LC1a) radar front ends achieve speed resolutions of 0.089 m/s (0.322 km/h) and 0.125 m/s (0.45 km/h), respectively, and the FMCW unit achieves a range resolution of 0.834 m. The study combines simulation models developed in LabVIEW with experimental electronic circuits used to evaluate the system behavior under different traffic conditions. Several scenarios were analyzed in which the signal timing was varied according to the number and type of vehicles, the presence of pedestrians and the air quality. A fuzzy logic controller was also implemented to improve the conditions of pedestrians waiting at signalized intersections. The results demonstrate the operation of the proposed architecture in all investigated scenarios and illustrate how the signal timing adapts to changing traffic and environmental parameters. In 30 simulation runs of 15 min at 1200 veh/h, the proposed controller reduced the mean vehicle waiting time by 20% and the pedestrian waiting time by 13% compared with fixed-time control, whereas the estimated CO₂ reduction was small (about 3%). The system is compared with representative approaches from the literature, and its limitations and the remaining research gaps are discussed. The validation presented here is limited to laboratory experiments, LabVIEW simulations and two outdoor gas-sensor campaigns; field tests at real intersections have not yet been performed. Nevertheless, the results indicate that the proposed architecture can support adaptive traffic management and provide a basis for further development and validation in real urban environments.