ABSTRACT Journal of Experimental Biology has a long history of reporting research discoveries on animal echolocation, the subject of this Centenary Review. Echolocating animals emit intense sound pulses and process echoes to localize objects in dynamic soundscapes. More than 1100 species of bats and 70 species of toothed whales rely on echolocation to operate in aerial and aquatic environments, respectively. The need to mitigate acoustic clutter and ambient noise is common to both aerial and aquatic echolocating animals, resulting in convergence of many echolocation features, such as directional sound emission and hearing, and decreased pulse intervals and sound intensity during target approach. The physics of sound transmission in air and underwater constrains the production, detection and localization of sonar signals, resulting in differences in response times to initiate prey interception by aerial and aquatic echolocating animals. Anti-predator behavioral responses of prey pursued by echolocating animals affect behavioral foraging strategies in air and underwater. For example, many insect prey can detect and react to bat echolocation sounds, whereas most fish and squid are unresponsive to toothed whale signals, but can instead sense water movements generated by an approaching predator. These differences have implications for how bats and toothed whales hunt using echolocation. Here, we consider the behaviors used by echolocating mammals to (1) track and intercept moving prey equipped with predator detectors, (2) interrogate dynamic sonar scenes and (3) exploit visual and passive acoustic stimuli. Similarities and differences in animal sonar behaviors underwater and in air point to open research questions that are ripe for exploration.
more »
« less
Sounding the Call for a Global Library of Underwater Biological Sounds
Aquatic environments encompass the world’s most extensive habitats, rich with sounds produced by a diversity of animals. Passive acoustic monitoring (PAM) is an increasingly accessible remote sensing technology that uses hydrophones to listen to the underwater world and represents an unprecedented, non-invasive method to monitor underwater environments. This information can assist in the delineation of biologically important areas via detection of sound-producing species or characterization of ecosystem type and condition, inferred from the acoustic properties of the local soundscape. At a time when worldwide biodiversity is in significant decline and underwater soundscapes are being altered as a result of anthropogenic impacts, there is a need to document, quantify, and understand biotic sound sources–potentially before they disappear. A significant step toward these goals is the development of a web-based, open-access platform that provides: (1) a reference library of known and unknown biological sound sources (by integrating and expanding existing libraries around the world); (2) a data repository portal for annotated and unannotated audio recordings of single sources and of soundscapes; (3) a training platform for artificial intelligence algorithms for signal detection and classification; and (4) a citizen science-based application for public users. Although individually, these resources are often met on regional and taxa-specific scales, many are not sustained and, collectively, an enduring global database with an integrated platform has not been realized. We discuss the benefits such a program can provide, previous calls for global data-sharing and reference libraries, and the challenges that need to be overcome to bring together bio- and ecoacousticians, bioinformaticians, propagation experts, web engineers, and signal processing specialists (e.g., artificial intelligence) with the necessary support and funding to build a sustainable and scalable platform that could address the needs of all contributors and stakeholders into the future.
more »
« less
- NSF-PAR ID:
- 10341027
- Date Published:
- Journal Name:
- Frontiers in Ecology and Evolution
- Volume:
- 10
- ISSN:
- 2296-701X
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Background Mosquitoes and the diseases they transmit pose a significant public health threat worldwide, causing more fatalities than any other animal. To effectively combat this issue, there is a need for increased public awareness and mosquito control. However, traditional surveillance programs are time-consuming, expensive, and lack scalability. Fortunately, the widespread availability of mobile devices with high-resolution cameras presents a unique opportunity for mosquito surveillance. In response to this, the Global Mosquito Observations Dashboard (GMOD) was developed as a free, public platform to improve the detection and monitoring of invasive and vector mosquitoes through citizen science participation worldwide.
Methods GMOD is an interactive web interface that collects and displays mosquito observation and habitat data supplied by four datastreams with data generated by citizen scientists worldwide. By providing information on the locations and times of observations, the platform enables the visualization of mosquito population trends and ranges. It also serves as an educational resource, encouraging collaboration and data sharing. The data acquired and displayed on GMOD is freely available in multiple formats and can be accessed from any device with an internet connection.
Results Since its launch less than a year ago, GMOD has already proven its value. It has successfully integrated and processed large volumes of real-time data (~ 300,000 observations), offering valuable and actionable insights into mosquito species prevalence, abundance, and potential distributions, as well as engaging citizens in community-based surveillance programs.
Conclusions GMOD is a cloud-based platform that provides open access to mosquito vector data obtained from citizen science programs. Its user-friendly interface and data filters make it valuable for researchers, mosquito control personnel, and other stakeholders. With its expanding data resources and the potential for machine learning integration, GMOD is poised to support public health initiatives aimed at reducing the spread of mosquito-borne diseases in a cost-effective manner, particularly in regions where traditional surveillance methods are limited. GMOD is continually evolving, with ongoing development of powerful artificial intelligence algorithms to identify mosquito species and other features from submitted data. The future of citizen science holds great promise, and GMOD stands as an exciting initiative in this field.
-
null (Ed.)The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert data scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge.more » « less
-
more » « less
Abstract People across the world seek out beautiful sounds in nature, such as a babbling brook or a nightingale song, for positive human experiences. However, it is unclear whether this positive aesthetic response is driven by a preference for the perceptual features typical of nature sounds versus a higher‐order association of nature with beauty. To test these hypotheses, participants provided aesthetic judgments for nature and urban soundscapes that varied on ease of recognition. Results demonstrated that the aesthetic preference for nature soundscapes was eliminated for the sounds hardest to recognize, and moreover the relationship between aesthetic ratings and several measured acoustic features significantly changed as a function of recognition. In a follow‐up experiment, requiring participants to classify these difficult‐to‐identify sounds into nature or urban categories resulted in a robust preference for nature sounds and a relationship between aesthetic ratings and our measured acoustic features that was more typical of easy‐to‐identify sounds. This pattern of results was replicated with computer‐generated artificial noises, which acoustically shared properties with the nature and urban soundscapes but by definition did not come from these environments. Taken together, these results support the conclusion that the recognition of a sound as either natural or urban dynamically organizes the relationship between aesthetic preference and perceptual features and that these preferences are not inherent to the acoustic features. Implications for nature's role in cognitive and affective restoration are discussed.
-
null (Ed.)Abstract Background Autonomous underwater vehicles (AUVs) and animal telemetry have become important tools for understanding the relationships between aquatic organisms and their environment, but more information is needed to guide the development and use of AUVs as effective animal tracking platforms. A forward-facing acoustic telemetry receiver (VR2Tx 69 kHz; VEMCO, Bedford, Nova Scotia) attached to a novel AUV (gliding robotic fish) was tested in a freshwater lake to (1) compare its detection efficiency (i.e., the probability of detecting an acoustic signal emitted by a tag) of acoustic tags (VEMCO model V8-4H 69 kHz) to stationary receivers and (2) determine if detection efficiency was related to distance between tag and receiver, direction of movement (toward or away from transmitter), depth, or pitch. Results Detection efficiency for mobile (robot-mounted) and stationary receivers were similar at ranges less than 300 m, on average across all tests, but detection efficiency for the mobile receiver decreased faster than for stationary receivers at distances greater than 300 m. Detection efficiency was higher when the robot was moving toward the transmitter than when moving away from the transmitter. Detection efficiency decreased with depth (surface to 4 m) when the robot was moving away from the transmitter, but depth had no significant effect on detection efficiency when the robot was moving toward the transmitter. Detection efficiency was higher when the robot was descending (pitched downward) than ascending (pitched upward) when moving toward the transmitter, but pitch had no significant effect when moving away from the transmitter. Conclusion Results suggested that much of the observed variation in detection efficiency is related to shielding of the acoustic signal by the robot body depending on the positions and orientation of the hydrophone relative to the transmitter. Results are expected to inform hardware, software, and operational changes to gliding robotic fish that will improve detection efficiency. Regardless, data on the size and shape of detection efficiency curves for gliding robotic fish will be useful for planning future missions and should be relevant to other AUVs for telemetry. With refinements, gliding robotic fish could be a useful platform for active tracking of acoustic tags in certain environments.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/fevo.2022.810156
