General audio tagging with ensembling convolutional neural networks and statistical features

Xu, Kele; Zhu, Boqing; Kong, Qiuqiang; Mi, Haibo; Ding, Bo; Wang, Dezhi; Wang, Huaimin

doi:10.1121/1.5111059

Cited by 23 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yan Xiong Li et al [22] used the BLSTM Network on Acoustic Scenes to get a better result. Kele Xu et al [23] purpose a novel ensemble-learning system consists of CNN that gets a superior classification performance.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Heartbeat Sound Signal Classification Using Deep Learning

Raza

Mehmood

Ullah

et al. 2019

Sensors

109

View full text Add to dashboard Cite

Presently, most deaths are caused by heart disease. To overcome this situation, heartbeat sound analysis is a convenient way to diagnose heart disease. Heartbeat sound classification is still a challenging problem in heart sound segmentation and feature extraction. Dataset-B applied in this study that contains three categories Normal, Murmur and Extra-systole heartbeat sound. In the purposed framework, we remove the noise from the heartbeat sound signal by applying the band filter, After that we fixed the size of the sampling rate of each sound signal. Then we applied down-sampling techniques to get more discriminant features and reduce the dimension of the frame rate. However, it does not affect the results and also decreases the computational power and time. Then we applied a purposed model Recurrent Neural Network (RNN) that is based on Long Short-Term Memory (LSTM), Dropout, Dense and Softmax layer. As a result, the purposed method is more competitive compared to other methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Most of the author [20,21,23] used CNN that performs well on image classification also RNN [24] performs well on a series of data. Image data gives the data as a 2D array that consists of the pixel value.…”

Section: Related Workmentioning

confidence: 99%

Heartbeat Sound Signal Classification Using Deep Learning

Raza

Mehmood

Ullah

et al. 2019

Sensors

109

View full text Add to dashboard Cite

show abstract

“…Subsequent use of this level of anxiety to adapt to the scenario of VR exposure therapy can be facilitated by classifying it into several intensity categories according to an evaluation scale. Among the algorithms that obtained a high classification accuracy are the classical machine learning methods and the convolutional neural networks (CNNs) [90,91].…”

Section: Classificationmentioning

confidence: 99%

Integrating Biosignals Measurement in Virtual Reality Environments for Anxiety Detection

Petrescu

Mitruț

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper proposes a protocol for the acquisition and processing of biophysical signals in virtual reality applications, particularly in phobia therapy experiments. This protocol aims to ensure that the measurement and processing phases are performed effectively, to obtain clean data that can be used to estimate the users’ anxiety levels. The protocol has been designed after analyzing the experimental data of seven subjects who have been exposed to heights in a virtual reality environment. The subjects’ level of anxiety has been estimated based on the real-time evaluation of a nonlinear function that has as parameters various features extracted from the biophysical signals. The highest classification accuracy was obtained using a combination of seven heart rate and electrodermal activity features in the time domain and frequency domain.

show abstract

“…After the feature extraction component, the relationship between extracted features and the popularity score can be built using many off-the-shelf regression models, which including Support Vector Machine (SVM), Random Forest [19] and Gradient boosting trees [6,43]. In our framework, we employ deep neural network as the regression model, by using the features extracted from different modalities.…”

Section: Neural Network-based Regression Model With Attention Mechanismmentioning

confidence: 99%

Multimodal Deep Learning for Social Media Popularity Prediction With Attention Mechanism

Lin

Zhao

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Social media popularity estimation refers to predict the post's popularity using multimodal contents. The prediction performance heavily relies on the feature extraction part and fully leveraging multimodal heterogeneous data is of a great challenge in the practical settings. Despite remarkable progress have been made, most of the previous attempts are restrained from the essentially limited property of the employed single modality. Inspired by the recent success of multimodal learning, we propose a novel multimodal deep learning framework for the popularity prediction task, which aims to leverage the complementary knowledge from different modalities. Moreover, an attention mechanism is introduced in our framework, with the goal to assign large weights to specified modalities during the training and inference phases. To empirically investigate the effectiveness and robustness of the proposed approach, we conduct extensive experiments on the 2020 SMP challenge. The obtained results show that the proposed framework outperforms related approaches. CCS CONCEPTS • Human-centered computing Collaborative and social computing systems and tools; • Social and professional topics;

show abstract

General audio tagging with ensembling convolutional neural networks and statistical features

Cited by 23 publications

References 21 publications

Heartbeat Sound Signal Classification Using Deep Learning

Heartbeat Sound Signal Classification Using Deep Learning

Integrating Biosignals Measurement in Virtual Reality Environments for Anxiety Detection

Multimodal Deep Learning for Social Media Popularity Prediction With Attention Mechanism

Contact Info

Product

Resources

About