A Novel Bird Sound Recognition Method Based on Multifeature Fusion and a Transformer Encoder.

Birds play a vital role in the study of ecosystems and biodiversity. Accurate bird identification helps monitor biodiversity, understand the functions of ecosystems, and develop effective conservation strategies. However, previous bird sound recognition methods often relied on single features and overlooked the spatial information associated with these features, leading to low accuracy. Recognizing this gap, the present study proposed a bird sound recognition method that employs multiple convolutional neural-based networks and a transformer encoder to provide a reliable solution for identifying and classifying birds based on their unique sounds. We manually extracted various acoustic features as model inputs, and feature fusion was applied to obtain the final set of feature vectors. Feature fusion combines the deep features extracted by various networks, resulting in a more comprehensive feature set, thereby improving recognition accuracy. The multiple integrated acoustic features, such as mel frequency cepstral coefficients (MFCC), chroma features (Chroma) and Tonnetz features, were encoded by a transformer encoder. The transformer encoder effectively extracted the positional relationships between bird sound features, resulting in enhanced recognition accuracy. The experimental results demonstrated the exceptional performance of our method with an accuracy of 97.99%, a recall of 96.14%, an F1 score of 96.88% and a precision of 97.97% on the Birdsdata dataset. Furthermore, our method achieved an accuracy of 93.18%, a recall of 92.43%, an F1 score of 93.14% and a precision of 93.25% on the Cornell Bird Challenge 2020 (CBC) dataset.

Factors Influencing Public Participation in Community Disaster Mitigation Activities: A Comparison of Model and Nonmodel Disaster Mitigation Communities.

Public participation in community-organized disaster mitigation activities is important for improving disaster mitigation capacity. With data from 260 questionnaires, this study compared the current status of public participation in model disaster mitigation communities and nonmodel communities in a geological-disaster-prone area. Three community-organized disaster mitigation education activities were compared cross-sectionally. A binary logistic regression was used to analyze the effects of attitude, perceived behavioral control, disaster experience, and other key factors on the public's choice to participate in community disaster mitigation activities. The analysis results indicated that model communities had higher public participation in two efforts, evacuation drills and self-help skills training, and lower participation in activities that invited them to express their feedback than nonmodel communities. The influence of attitudinal factors on the decision to participate in disaster mitigation activities had a high similarity across community types. The public participation in model disaster mitigation communities is influenced by factors such as subjective norms and participation cognition; the behavior of people in nonmodel communities is influenced by factors such as previous experience with disasters, perceived behavioral control, risk perception, and participation cognition and has a greater potential for disaster mitigation community construction. This study provides practical evidence and theoretical support for strengthening the sustainable development of disaster mitigation community building.

Phthalate esters in main source water and drinking water of Zhejiang Province (China): Distribution and health risks.

To evaluate the distributions and health risks of phthalate esters in the main source water and corresponding drinking water of Zhejiang Province, the concentrations of 16 phthalate esters in water samples from 19 sites were measured from samples taken in the dry season and wet season. The concentration of the total phthalate ester congeners in source water ranged from 1.07 µg/L to 7.12 µg/L in the wet season, from 0.01 µg/L to 1.58 µg/L in the dry season, from 1.18 µg/L to 15.28 µg/L from drinking water in the wet season, and from 0.16 µg/L to 1.86 µg/L from drinking water in the dry season. Of the 16 phthalate esters, dimethyl phthalate, dibutyl phthalate, di-(2-ethyl-hexyl) phthalate, di-iso-butyl phthalate, bis-2-n-butoxyethyl phthalate, and dicyclohexyl phthalate were present in the samples analyzed, dominated by di-iso-butyl phthalate and di-(2-ethyl-hexyl) phthalate. The concentrations of phthalate esters in the wet season were all relatively higher than those in the dry season, and the drinking water had higher concentrations of phthalate esters than source water. The phthalate ester congeners studied pose little health risk to nearby citizens. Environ Toxicol Chem 2015;34:2205-2212. © 2015 SETAC.