In the last two decades, the increased production and installation of photovoltaic (PV) plants worldwide has asked for efficient low-cost methods for PV plant inspection to monitor their functionality and guaranteed their performance. To lower maintenance costs new systems have been thought to substitute human workers inspecting the PV plants. The employment of Unmanned Aerial Vehicles (UAVs) has allowed realizing a fast detection of defects and problems arisen in PV plants thanks to the fusion of computer vision algorithms and high accuracy Global Navigation Satellite System (GNSS) positioning techniques able to detect and tag anomalies and identify the defective panels. Authors in this paper intend to present the state-of-the-art in the Computer Vision field applied to PV plant inspection and to thermal anomalies detection over the panels. In addition, different data sets have been recorded and compared for geo-referencing the solar panels. They have been derived through the U-blox NEO-M8N installed on board of the UAV used for inspection. Although the U-blox NEO-M8N measures are less accurate than the classic RTK GNSS ones, the measurements obtained with this handset introduce a very interesting novelty since initial services of the Galileo constellation, supported by the NEO-M8N GNSS module, have become available only since last December. Future testing and validation will be performed by using geo-referenced data from the RTK GNSS receiver, that has been ordered with a specially customized antenna whose specifications have been properly designed and sent to the manufacturer for its fabrication. Next campaigns will allow to get results also from this RTK receiver and to properly validate the proposed algorithm, by comparing new results with those found through the employment of U-blox receiver.

In the last two decades, growing attention on climate issues has caused the worldwide increase of Photovoltaic (PV) plant production and installation, and the consequent promotion of clean energy policies, with large amounts of incentives and funding made available in the specific sector by Governments and the European Economic Community itself. Increasing PV distribution and installation has to ask for efficient and low-cost methods for inspection to monitor functionality and guarantee performance. A big concern of PV plant owners is to rely on efficient maintenance procedures. Recognizing degradation and defects of PV cells is a very important issue to allow immediate intervention and substitution of modules to avoid output power losses and performance degradation.

Traditionally, process-aware Decision Support Systems (DSSs) have been enhanced with AI functionalities to facilitate quick and informed decision-making. In this context, AI-Augmented Business Process Management Systems have emerged as innovative human-centric information systems, blending flexibility, autonomy, and conversational capability. Large Language Models (LLMs) have significantly boosted such systems, showcasing remarkable natural language processing capabilities across various tasks. Despite the potential of LLMs to support human decisions in business contexts, empirical validations of their effectiveness for process-aware decision support are scarce in the literature. In this paper, we propose the Business Process Large Language Model (BPLLM) framework, a novel approach for enacting actionable conversations with human workers. BPLLM couples Retrieval-Augmented Generation with fine-tuning, to enrich process-specific knowledge. Additionally, a process-aware chunking approach is incorporated to enhance the BPLLM pipeline. We evaluated the approach in various experimental scenarios to assess its ability to generate accurate and contextually relevant answers to users’ questions. The empirical study shows the promising performance of the framework in identifying the presence of particular activities and sequence flows within the considered process model, offering insights into its potential for enhancing process-aware DSSs.

Anomaly detection in network traffic is a hot and ongoing research theme especially when concerning IoT devices, which are quickly spreading throughout various situations of people’s life and, at the same time, prone to be attacked through different weak points. In this paper, we tackle the emerging anomaly detection problem in IoT, by integrating five different datasets of abnormal IoT traffic and evaluating them with a deep learning approach capable of identifying both normal and malicious IoT traffic as well as different types of anomalies. The large integrated dataset is aimed at providing a realistic and still missing benchmark for IoT normal and abnormal traffic, with data coming from different IoT scenarios. Moreover, the deep learning approach has been enriched through a proper hyperparameter optimization phase, a feature reduction phase by using an autoencoder neural network, and a study of the robustness of the best considered deep neural networks in situations affected by Gaussian noise over some of the considered features. The obtained results demonstrate the effectiveness of the created IoT dataset for anomaly detection using deep learning techniques, also in a noisy scenario.