English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

This paper presents a successful application of deep learning for objectrecognition based on acoustic data. The shortcomings of previously employedapproaches where handcrafted features describing the acoustic data are beingused, include limiting the capability of the found representation to be widelyapplicable and facing the risk of capturing only insignificant characteristicsfor a task. In contrast, there is no need to define the feature representationformat when using multilayer/deep learning architecture methods: features canbe learned from raw sensor data without defining discriminative characteristicsa-priori. In this paper, stacked denoising autoencoders are applied to train adeep learning model. Knocking each object in our test set 120 times with amarker pen to obtain the auditory data, thirty different objects weresuccessfully classified in our experiment and each object was knocked 120 timesby a marker pen to obtain the auditory data. By employing the proposed deeplearning framework, a high accuracy of 91.50% was achieved. A traditionalmethod using handcrafted features with a shallow classifier was taken as abenchmark and the attained recognition rate was only 58.22%. Interestingly, arecognition rate of 82.00% was achieved when using a shallow classifier withraw acoustic data as input. In addition, we could show that the time taken toclassify one object using deep learning was far less (by a factor of more than6) than utilizing the traditional method. It was also explored how differentmodel parameters in our deep architecture affect the recognition performance.

Knock-Knock: Acoustic Object Recognition by using Stacked Denoising Autoencoders