More Like this

1. Classifying Humpback Whale Calls to Song and Non-Song Vocalizations using Bag of Words Descriptor on Acoustic Data

   https://doi.org/10.1109/ICMLA.2019.00150  

   Mohebbi-Kalkhoran, Hamed ; Zhu, Chenyang ; Schinault, Matthew ; Ratilal, Purnima ( December 2019 , 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA))

   Humpback whale behavior, population distribution and structure can be inferred from long term underwater passive acoustic monitoring of their vocalizations. Here we develop automatic approaches for classifying humpback whale vocalizations into the two categories of song and non-song, employing machine learning techniques. The vocalization behavior of humpback whales was monitored over instantaneous vast areas of the Gulf of Maine using a large aperture coherent hydrophone array system via the passive ocean acoustic waveguide remote sensing technique over multiple diel cycles in Fall 2006. We use wavelet signal denoising and coherent array processing to enhance the signal-to-noise ratio. To build features vector for every time sequence of the beamformed signals, we employ Bag of Words approach to time-frequency features. Finally, we apply Support Vector Machine (SVM), Neural Networks, and Naive Bayes to classify the acoustic data and compare their performances. Best results are obtained using Mel Frequency Cepstrum Coefficient (MFCC) features and SVM which leads to 94% accuracy and 72.73% F1-score for humpback whale song versus non-song vocalization classification, showing effectiveness of the proposed approach for real-time classification at sea. 

   more » « less
2. Rapid 1024-pixel Electrochemical Imaging at 10,000 Frames per Second using Monolithic CMOS Sensor and Multifunctional Data Acquisition System

   https://doi.org/10.1109/JSEN.2018.2835829  

   White, Kevin A. ; Mulberry, Geoffrey ; Kim, Brian N. ( May 2018 , IEEE Sensors Journal)

   Fast electrochemical imaging enables the dynamic study of electroactive molecule diffusion in neurotransmitter release from single cells and dopamine mapping in brain slices. In this paper, we discuss the design of an electrochemical imaging sensor using a monolithic CMOS sensor array and a multifunctional data acquisition system. Using post-CMOS fabrication, the CMOS sensor integrates 1024 on-chip electrodes on the surface and contains 1024 low-noise amplifiers to simultaneous process parallel electrochemical recordings. Each electrochemical electrode and amplifier are optimized to operate at 10.38 kHz sampling rate. To support the operation of the high-throughput CMOS device, a multifunctional data acquisition device is developed to provide the required speed and accuracy. The high analog data rate of 10.63 MHz from all 1024 amplifiers is redundantly sampled by the custom-designed data acquisition system which can process up to 73.6 MHz with up to ~400 Mbytes/s data rate to a computer using USB 3.0 interface. To contain the liquid above the electrochemical sensors and prevent electronic and wire damage, we packaged the monolithic sensor using a 3D-printed well. Using the presented device, 32 pixel × 32 pixel electrochemical imaging of dopamine diffusion is successfully demonstrated at over 10,000 frames per second, the fastest reported to date. 

   more » « less
3. Comparing Performances of Five Distinct Automatic Classifiers for Fin Whale Vocalizations in Beamformed Spectrograms of Coherent Hydrophone Array

   https://doi.org/10.3390/rs12020326  

   Garcia, Heriberto A. ; Couture, Trenton ; Galor, Amit ; Topple, Jessica M. ; Huang, Wei ; Tiwari, Devesh ; Ratilal, Purnima ( January 2020 , Remote Sensing)

   A large variety of sound sources in the ocean, including biological, geophysical, and man-made, can be simultaneously monitored over instantaneous continental-shelf scale regions via the passive ocean acoustic waveguide remote sensing (POAWRS) technique by employing a large-aperture densely-populated coherent hydrophone array system. Millions of acoustic signals received on the POAWRS system per day can make it challenging to identify individual sound sources. An automated classification system is necessary to enable sound sources to be recognized. Here, the objectives are to (i) gather a large training and test data set of fin whale vocalization and other acoustic signal detections; (ii) build multiple fin whale vocalization classifiers, including a logistic regression, support vector machine (SVM), decision tree, convolutional neural network (CNN), and long short-term memory (LSTM) network; (iii) evaluate and compare performance of these classifiers using multiple metrics including accuracy, precision, recall and F1-score; and (iv) integrate one of the classifiers into the existing POAWRS array and signal processing software. The findings presented here will (1) provide an automatic classifier for near real-time fin whale vocalization detection and recognition, useful in marine mammal monitoring applications; and (2) lay the foundation for building an automatic classifier applied for near real-time detection and recognition of a wide variety of biological, geophysical, and man-made sound sources typically detected by the POAWRS system in the ocean. 

   more » « less
4. The Southern Ocean Exchange: porous boundaries between humpback whale breeding populations in southern polar waters

   https://doi.org/10.1038/s41598-021-02612-5  

   Marcondes, M. C. C. ; Cheeseman, T. ; Jackson, J. A. ; Friedlaender, A. S. ; Pallin, L. ; Olio, M. ; Wedekin, L. L. ; Daura-Jorge, F. G. ; Cardoso, J. ; Santos, J. D. F. ; et al ( December 2021 , Scientific Reports)

   Humpback whales (Megaptera novaeangliae) are a cosmopolitan species and perform long annual migrations between low-latitude breeding areas and high-latitude feeding areas. Their breeding populations appear to be spatially and genetically segregated due to long-term, maternally inherited fidelity to natal breeding areas. In the Southern Hemisphere, some humpback whale breeding populations mix in Southern Ocean waters in summer, but very little movement between Pacific and Atlantic waters has been identified to date, suggesting these waters constituted an oceanic boundary between genetically distinct populations. Here, we present new evidence of summer co-occurrence in the West Antarctic Peninsula feeding area of two recovering humpback whale breeding populations from the Atlantic (Brazil) and Pacific (Central and South America). As humpback whale populations recover, observations like this point to the need to revise our perceptions of boundaries between stocks, particularly on high latitude feeding grounds. We suggest that this “Southern Ocean Exchange” may become more frequent as populations recover from commercial whaling and climate change modifies environmental dynamics and humpback whale prey availability.

    

   more » « less
5. The Wire Flyer Towed Profiling System

   https://doi.org/DOI: 10.1175/JTECH-D-17-0180.1  

   Roman, C. ; Ullman, D.S. ; Hebert, D. ; Licht, S. ( January 2019 , Journal of atmospheric and oceanic technology)

   The Wire Flyer towed vehicle is a new platform able to collect high-resolution water column sections. The vehicle is motivated by a desire to effectively capture spatial structures at the submesoscale. The vehicle fills a niche that is not achieved by other existing towed and repeat profiling systems. The Wire Flyer profiles up and down along a ship-towed cable autonomously using controllable wings for propulsion. At ship speeds between 2 and 5 kt (1.02–2.55ms21), the vehicle is able to profile over prescribed depth bands down to 1000 m. The vehicle carries sensors for conductivity, temperature, depth, oxygen, turbidity, chlorophyll, pH, and oxidation reduction potential. During normal operations the vehicle is typically commanded to cover vertical regions between 300 and 400min height with profiles that repeat at kilometer spacing. The vertical profiling speed can be user specified up to 150mmin21. The high-density sampling capability at depths below the upper few hundred meters makes the vehicle distinct from other systems. During operations an acoustic modem is used to communicate with the vehicle to provide status information, data samples, and the ability to modify the sampling pattern. This paper provides an overview of the vehicle system, describes its operation, and presents results from several cruises. 

   more » « less