Underwater acoustic target classification based on u-shaped network
Time: 8:00 am
Author: lingzhi xue
Abstract ID: 1820
Target recognition is a key task and a difficult technique in underwater acoustic signal processing. One of the most challenging problem is that the label information of the underwater acoustic samples is scarce or missing. To solve the problem, this paper presents a local skip connection u-shaped architecture network(U-Net)based on the convolutional neural network(CNN).To this end, the network architecture is designed cleverly to generate a contracting path and an expansive path to achieve the extraction of different scale features. More importantly, a local skip connection mechanism is proposed to optimize classification rates by reusing former feature maps in contracting path. The experimental results of the measured dataset demonstrate the recognition accuracy of the model is better than that of deep belief network(DBN) and generative adversarial network(GAN) networks.Further research on three kinds of network by visualization method shows that the proposed network can learn more effective feature information with limited samples.
You must be logged in to download paper. Click here to login
Ferry M/V Kramer noise mitigation
Time: 8:40 am
Author: Michael Bahtiarian
Abstract ID: 2060
The Motor Vessel (M/V) Edward V. Kramer is an aluminum vessel that operates as a small passenger ferry, which is owned and operated by the Department of Homeland Security (DHS) and used to transport DHS personnel and materials to Plum Island, NY. It was placed in service in 2018 and right from the start the sound levels inside the Main Deck compartment were found to be excessive. The original vessel specification included a noise limit of 75 dBA in the Main Deck Passenger Lounge and measured levels were as high as 87 dBA. A ship survey of sound and vibration was performed. Noise predictions to determine the controlling sound paths was also performed based on engine sound and vibration source levels. Recommendations for mitigation were presented and carried out by another shipyard. Mitigation included vibration isolation of the main engines and sound attenuation improvements to the Main Deck Passenger Lounge. After completion of the modifications, another survey was performed in 2021 and results show a reduction by as much as 11 dB in the Main Deck Passenger lounge. Noise estimation methods and details on the noise control treatments are given in the paper.
You must be logged in to download paper. Click here to login
Acoustic survey at Genova (Italy) Aquarium aiming at characterizing the acoustic of tropical marine environment
Time: 8:20 am
Author: Giovanni Zambon
Abstract ID: 2411
An acoustics survey has been performed at Genova (Italy) Aquarium aiming at characterizing the acoustic environment of tropical underwater habitats. Mid-term (5-7 days) and short-term measurements (10-20 min) within different fish tanks containing tropical habitats have been chosen for a preliminary analysis. Eco-acoustic indices and statistical-related acoustic indices have been applied to derive information on the population activity and determine the bio-acoustic richness. Such approach will be used to compare environments with different degree of disturbance and derive information on the environmental quality of both artificial and natural habitats
You must be logged in to download paper. Click here to login