Multi-class Classification of Impulse and Non-impulse Sounds Using Deep Convolutional Neural Network (DCNN)

Abayomi‐Alli, Adebayo; Abayomi‐Alli, Olusola; Vipperman, Jeffrey S.; Odusami, Modupe; Misra, Sanjay

doi:10.1007/978-3-030-24308-1_30

Cited by 3 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of the results of the neural network [ 19 ] depends on the similarity of the TS from the training set and the predicted TS and on the completeness and redundancy of the training set. The training set contains metric values and forecast error values for each TS included in it.…”

Section: Neural Network For Selecting Prediction Methodsmentioning

confidence: 99%

An Approach to the Selection of a Time Series Analysis Method Using a Neural Network

Yashin

Moshkina

Moshkin

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, a technique for selecting individual methods in a combined time series forecasting model is described. A neural network at the input of which a vector of time series metrics is proposed. The metrics corresponds to significant characteristics of the time series. The values of the metrics are easily computed. The neural network calculates the estimated prediction error for each model from the base set of the combined model. The proposed selection method is most effective for short time series and when the base set contains a lot of complex prediction methods. The developed system was tested on the time series from the CIF 2015-2016 competitions. According to the result of the experiment, the application of the developed system allowed to reduce the average forecast error from 13 to 9 percent.

show abstract

Section: Neural Network For Selecting Prediction Methodsmentioning

confidence: 99%

An Approach to the Selection of a Time Series Analysis Method Using a Neural Network

Yashin

Moshkina

Moshkin

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…A large variety of deep learning modeling approaches for time series analysis have been exploited for a wide range of tasks, such as forecasting, regression, and classification [5, 9, 14 15, 36]. The most common established deep learning models in this area are convolutional neural network (CNN) [13,42,43], recurrent neural networks (RNN) [5,7,8], and attention-based neural networks [10,11,14,15,16,34]. Since CNN-based models can only learn local neighborhood features, recently, RNN-based models and attention-based models which can learn long-range dependencies are increasingly popular for learning from time series data [5].…”

Section: Deep Learning Approachesmentioning

confidence: 99%

Machine Learning Applied for Spectra Classification

Sun

Brockhauser

Hegedűs

2021

Computational Science and Its Applications – ICCSA 2021

View full text Add to dashboard Cite

Spectroscopy experiment techniques are widely used and produce a huge amount of data especially in facilities with very high repetition rates. In High Energy Density (HED) experiments with high-density materials, changes in pressure will cause changes in the spectral peak. Immediate feedback on the actual status (e.g. time-resolved status of the sample) would be essential to quickly judge how to proceed with the experiment. The two major spectral changes we aim to capture are either the change of intensity distribution (e.g., drop or appearance) of peaks at certain locations, or the shift of those on the spectrum. In this work, we apply recent popular machine learning/deep learning models to HED experimental spectra data classification. The models we presented range from supervised deep neural networks (state-of-the-art LSTM-based model and Transformer-based model) to unsupervised spectral clustering algorithm. These are the common architectures for time series processing. The PCA method is used as data preprocessing for dimensionality reduction. Three different ML algorithms are evaluated and compared for the classification task. The results show that all three methods can achieve 100% classification confidence. Among them, the spectra clustering method consumes the least calculation time (0.069 s), and the transformer-based method uses the most training time (0.204 s).

show abstract

“…Big data in healthcare have been established for its timely advancement in disease detection, diagnosis, and enable the best control of any disease outbreaks. Predictive analysis of health care can be achieved easily with the aid of big data [49,57]. In the United States of America, for example, predictive analytics was used to enhance disease response management and a deeper understanding of diseases [50].…”

Section: Big Data In the Healthcare Systemmentioning

confidence: 99%

Prediction of Malaria Fever Using Long-Short-Term Memory and Big Data

Awotunde

Jimoh

Oladipo

et al. 2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Malaria has been identified to be one of the most common diseases with a great public health problem globally and it is caused by mosquitos' parasites. This prevails in developing nations where healthcare facilities are not enough for the patients. The technological advancement in medicine has resulted in the collection of huge volumes of data from various sources in different formats. A reliable and early parasite-based diagnosis, identification of symptoms, disease monitoring, and prescription are crucial to decreasing malaria occurrence in Nigeria. Hence, the use of deep and machine learning models is essentials to reduce the effect of malaria-endemic and for better predictive models. Therefore, this paper proposes a framework to predict malaria-endemic in Nigeria. To predict the malaria-endemic well, both environmental and clinical data were used using Kwara State as a case study. The study used a deep learning algorithm as a classifier for the proposed system. Three locations were selected from Irepodun Local Government Areas of Kwara State with 34 months periodic pattern. Each location reacted differently based on environmental factors. The findings indicate that both factors are significant in malaria prediction and transmission. The LSTM algorithm provides an efficient method for detecting situations of widespread malaria.

show abstract

Multi-class Classification of Impulse and Non-impulse Sounds Using Deep Convolutional Neural Network (DCNN)

Cited by 3 publications

References 18 publications

An Approach to the Selection of a Time Series Analysis Method Using a Neural Network

An Approach to the Selection of a Time Series Analysis Method Using a Neural Network

Machine Learning Applied for Spectra Classification

Prediction of Malaria Fever Using Long-Short-Term Memory and Big Data

Contact Info

Product

Resources

About