We present a system that integrates diverse technologies to achieve real-time, distributed audio surveillance. The system employs a network of microphones mounted on ESP32 platforms, which transmit compressed audio chunks via an MQTT protocol to Raspberry Pi5 devices for acoustic classification. These devices host an audio transformer model trained on the AudioSet dataset, enabling the real-time classification and timestamping of audio events with high accuracy. The output of the transformer is kept in a database of events and is subsequently converted into JSON format. The latter is further parsed into a graph structure that encapsulates the annotated soundscape, providing a rich and dynamic representation of audio environments. These graphs are subsequently traversed and analyzed using dedicated Python code and large language models (LLMs), enabling the system to answer complex queries about the nature, relationships, and context of detected audio events. We introduce a novel graph parsing method that achieves low false-alarm rates. In the task of analyzing the audio from a 1 h and 40 min long movie featuring hazardous driving practices, our approach achieved an accuracy of 0.882, precision of 0.8, recall of 1.0, and an F1 score of 0.89. By combining the robustness of distributed sensing and the precision of transformer-based audio classification, our approach that treats audio as text paves the way for advanced applications in acoustic surveillance, environmental monitoring, and beyond.

Insects play essential roles in ecosystems, providing services such as pollination and pest regulation. However, global insect populations are in decline due to factors like habitat loss and climate change, raising concerns about ecosystem stability. Traditional insect monitoring methods are limited in scope, but advancements in AI and machine learning enable automated, non-invasive monitoring with camera traps. In this study, we leverage the new Diopsis dataset that contains images from field operations to explore an approach that emphasizes both background extraction from images and the SAHI approach. By creating augmented backgrounds from extracting insects from training images and using these backgrounds as canvases to artificially relocate insects, we can improve detection accuracy, reaching mAP50 72.7% with YOLO10nano, and reduce variability when counting insects on different backgrounds and image sizes, supporting efficient insect monitoring on low-power devices such as Raspberry Pi Zero W 2.

In previous research, we presented an apparatus designed for comprehensive and systematic surveillance of trees against borers. This apparatus entailed the insertion of an uncoated waveguide into the tree trunk, enabling the transmission of micro-vibrations generated by moving or digging larvae to a piezoelectric probe. Subsequent recordings were then transmitted at predetermined intervals to a server, where analysis was conducted manually to assess the infestation status of the tree. However, this method is hampered by significant limitations when scaling to monitor thousands of trees across extensive spatial domains. In this study, we address this challenge by integrating signal processing techniques capable of distinguishing vibrations attributable to borers from those originating externally to the tree. Our primary innovation involves quantifying the impulses resulting from the fracturing of wood fibers due to borer activity. The device employs criteria such as impulse duration and a strategy of waiting for periods of relative quietness before commencing the counting of impulses. Additionally, we provide an annotated large-scale database comprising laboratory and field vibrational recordings, which will facilitate further advancements in this research domain.