Few-shot (FS) sound event detection (SED) is the process of identifying and recognizing specific sounds or events within an audio recording, specifically in the field of bioacoustics. This task is especially challenging due to the substantial unpredictability, complexity of the sounds, and the limited amount of labeled training data available. We recommend a transudative learning technique with data augmentation in response to the recent success of transudative inference (TI) in the field of computer vision. It aims to make predictions about new, unseen data by maximizing the mutual information between features of the labeled training data and the features of the unlabeled test data. We use the detection and classification of acoustic scenes and events (DCASE)-2021 and DCASE-2022 official datasets from the DCASE to do FS bioacoustics event detection experiments. Research findings illustrate that the recommended approach using TI along with spectrogram augmentation improves the performance of the FS bioacoustics event detection system. The proposed method improves the F-score by 0.10 and 0.16 on DCASE-2021 and DCASE-2022, respectively, compared with the average baseline and state-of-the-art methods.

Deploying unmanned aerial vehicles (UAVs) as aerial base stations is an exceptional approach to reinforce terrestrial infrastructure owing to their remarkable flexibility and superior agility. However, it is essential to design their flight trajectory effectively to make the most of UAV-assisted wireless communications. This paper presents a novel method for improving wireless connectivity between UAVs and terrestrial users through effective path planning. This is achieved by developing a goal-directed trajectory planning method using active inference. First, we create a global dictionary using traveling salesman problem with profits (TSPWP) instances executed on various training examples. This dictionary represents the world model and contains letters representing available hotspots, tokens representing local paths, and words depicting complete trajectories and hotspot order. By using this world model, the UAV can understand the TSPWP’s decision-making grammar and how to use the available letters to form tokens and words at various levels of abstraction and time scales. With this knowledge, the UAV can assess encountered situations and deduce optimal routes based on the belief encoded in the world model. Our proposed method outperforms traditional Q-learning by providing fast, stable, and reliable solutions with good generalization ability.

Deploying UAVs as aerial base stations is an exceptional approach to reinforce terrestrial infrastructure owing to their remarkable flexibility and superior agility. However, it is essential to design their flight trajectory effectively to make the most of UAV-assisted wireless communications. This paper presents a novel method for improving wireless connectivity between UAVs and terrestrial users through effective path planning. This is achieved by developing a goal-directed trajectory planning method using active inference. First, we create a global dictionary using TSPWP instances executed on various training examples. This dictionary contains letters representing available hotspots, tokens representing local paths, and words depicting complete trajectories and hotspot order. By using this world model, the UAV can understand the TSPWP’s decision-making grammar and how to use the available letters to form tokens and words at various levels of abstraction and time scales. With this knowledge, the UAV can assess encountered situations and deduce optimal routes based on the belief encoded in the world model. Our proposed method outperforms traditional Q-learning by providing fast, stable, and reliable solutions with good generalization ability.