Smart soundscape sensing: A low-cost and integrated sensing system for urban soundscape ecology research

被引:7
作者
Wang, Jingyi [1 ,2 ]
Li, Chunming [1 ,4 ]
Lin, Yinglun [3 ]
Weng, Chen [1 ,2 ]
Jiao, Yaran [1 ,2 ]
机构
[1] Chinese Acad Sci, Inst Urban Environm, Fujian Key Lab Watershed Ecol, Key Lab Urban Environm & Hlth, Xiamen 361021, Peoples R China
[2] Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China
[3] Fujian Agr & Forestry Univ, Coll Resource & Environm Sci, Fuzhou 350002, Peoples R China
[4] Chinese Acad Sci, Inst Urban Environm, 1799 Jimei Rd, Xiamen, Fujian, Peoples R China
基金
中国国家自然科学基金;
关键词
Soundscape ecology; Machine learning; Intelligent workflow; Integrated data; Computer-based soundscape analysis; Sensor networks; ACOUSTIC INDEXES; BIODIVERSITY; CONSERVATION; MODEL; TREES; AREA; TOOL;
D O I
10.1016/j.eti.2022.102965
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Worldwide, cities are increasingly taking the burden of accommodating an extra population. It is undergoing the most extensive anthropogenic transformation of the landscape, the most predominant modification of biogeochemical processes, and the most intensive alteration of biological communities. These severe ecological stresses in cities urgently call for research on the coupled natural-human urban ecosystem. Soundscape, containing anthropogenic, biological, and geological elements, can provide rich information on natural and artificial environment. However, the main challenge is the discontinuity, high cost, and low efficiency of the existing manual acquisition and computation methods. It will limit the utilization of the mass data collected by the existing soundscape acquisition equipment, with the failure to reveal the pattern and dynamics included in the soundscape, in the meantime will obstruct the promising avenue for environmental research from the auditory perspective. Given the challenges, this paper introduces an innovative Smart Soundscape Sensing (SSS) system based on the intelligent sensor network and artificial intelligence (AI) technology. The technology fulfills three significant breakthroughs: (a) integrated data acquisition based on a multithreaded acquisition strategy; (b) efficient data transmission and storage based on alternative transmission modes and storage protocols; (c) multifunctional data analysis and visualization based on automatic computation and AI technologies. Results prove that SSS can effectively uncover the evolution of soundscape and its environment, and surpass traditional hand-crafted methods, especially in long-term projects. Applying such an integrated and intelligent system can facilitate drawing out hidden insights within the soundscape, refining urban sound environment planning, and delivering a sustainable future. (c) 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
引用
收藏
页数:14
相关论文
共 61 条
  • [1] Wildlife Insights: A Platform to Maximize the Potential of Camera Trap and Other Passive Sensor Wildlife Data for the Planet
    Ahumada, Jorge A.
    Fegraus, Eric
    Birch, Tanya
    Flores, Nicole
    Kays, Roland
    O'Brien, Timothy G.
    Palmer, Jonathan
    Schuttler, Stephanie
    Zhao, Jennifer Y.
    Jetz, Walter
    Kinnaird, Margaret
    Kulkarni, Sayali
    Lyet, Arnaud
    Thau, David
    Duong, Michelle
    Oliver, Ruth
    Dancer, Anthony
    [J]. ENVIRONMENTAL CONSERVATION, 2020, 47 (01) : 1 - 6
  • [2] Real-time bioacoustics monitoring and automated species identification
    Aide, T. Mitchell
    Corrada-Bravo, Carlos
    Campos-Cerqueira, Marconi
    Milan, Carlos
    Vega, Giovany
    Alvarez, Rafael
    [J]. PEERJ, 2013, 1
  • [3] Ecological resilience in urban ecosystems: Linking urban patterns to human and ecological functions
    Marina Alberti
    John M. Marzluff
    [J]. Urban Ecosystems, 2004, 7 (3) : 241 - 265
  • [4] FIWARE based low-cost wireless acoustic sensor network for monitoring and classification of urban soundscape
    Arce, Pau
    Salvo, David
    Pinero, Gema
    Gonzalez, Alberto
    [J]. COMPUTER NETWORKS, 2021, 196
  • [5] Guidelines for the use of acoustic indices in environmental research
    Bradfer-Lawrence, Tom
    Gardner, Nick
    Bunnefeld, Lynsey
    Bunnefeld, Nils
    Willis, Stephen G.
    Dent, Daisy H.
    [J]. METHODS IN ECOLOGY AND EVOLUTION, 2019, 10 (10): : 1796 - 1807
  • [6] Brown AL, 2012, INT J ACOUST VIB, V17, P73
  • [7] A synthesis of health benefits of natural sounds and their distribution in national parks
    Buxton, Rachel T.
    Pearson, Amber L.
    Allou, Claudia
    Fristrup, Kurt
    Wittemyer, George
    [J]. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2021, 118 (14)
  • [8] Efficacy of extracting indices from large-scale acoustic recordings to monitor biodiversity
    Buxton, Rachel T.
    McKenna, Megan F.
    Clapp, Mary
    Meyer, Erik
    Stabenau, Erik
    Angeloni, Lisa M.
    Crooks, Kevin
    Wittemyer, George
    [J]. CONSERVATION BIOLOGY, 2018, 32 (05) : 1174 - 1184
  • [9] Identifying Leaf Phenology of Deciduous Broadleaf Forests from PhenoCam Images Using a Convolutional Neural Network Regression Method
    Cao, Mengying
    Sun, Ying
    Jiang, Xin
    Li, Ziming
    Xin, Qinchuan
    [J]. REMOTE SENSING, 2021, 13 (12)
  • [10] Automatic standardized processing and identification of tropical bat calls using deep learning approaches
    Chen, Xing
    Zhao, Jun
    Chen, Yan-hua
    Zhou, Wei
    Hughes, Alice C.
    [J]. BIOLOGICAL CONSERVATION, 2020, 241