Autoencoder Neural Networks for Outlier Correction in ECG- Based Biometric Identification

Karpinski, Mikolaj; Khoma, Volodymyr; Dudvkevych, Valerii; Khoma, Y.V.; Sabodashko, Dmytro

doi:10.1109/idaacs-sws.2018.8525836

Cited by 17 publications

(14 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Comparing with research [14], our deep learning method has better performance than other machine learning methods. Researcher Arden evaluates the performance of ReLU activation function [15] but according to our research for English to Bangla translation tanh and linear activation works well in the encoder-decoder layer. Our verification shows that the proposed computational technique acquires better performance as a traditional translation.…”

Section: Discussionmentioning

confidence: 99%

English to Bangla Machine Translation Using Recurrent Neural Network

Siddique¹,

Ahmed²,

Talukder³

et al. 2020

IJFCC

View full text Add to dashboard Cite

The applications of recurrent neural networks in machine translation are increasing in natural language processing. Besides other languages, Bangla language contains a large amount of vocabulary. Improvement of English to Bangla machine translation would be a significant contribution to Bangla Language processing. This paper describes an architecture of English to Bangla machine translation system. The system has been implemented with the encoder-decoder recurrent neural network. The model uses a knowledge-based context vector for the mapping of English and Bangla words. Performances of the model based on activation functions are measured here. The best performance is achieved for the linear activation function in encoder layer and the tanh activation function in decoder layer. From the execution of GRU and LSTM layer, GRU performed better than LSTM. The attention layers are enacted with softmax and sigmoid activation function. The approach of the model outperforms the previous state-of-the-art systems in terms of cross-entropy loss metrics. The reader can easily find out the structure of the machine translation of English to Bangla and the efficient activation functions from the paper.

show abstract

Section: Discussionmentioning

confidence: 99%

English to Bangla Machine Translation Using Recurrent Neural Network

Siddique¹,

Ahmed²,

Talukder³

et al. 2020

IJFCC

View full text Add to dashboard Cite

show abstract

“…In order to identify and repair ECG heartbeat outliers, Karpinski et al 20 presented a unique approach based on autoencoder neural networks. Major waveform aberrations in heartbeats are frequently regarded as abnormal and excluded.…”

Section: Literature Reviewmentioning

confidence: 99%

HGSSA-bi LSTM: A Secure Multimodal Biometric Sensing Using Optimized Bi-Directional Long Short-Term Memory with Self-Attention

Priyani,

Nanglia,

Singh

et al. 2024

ECS Sens. Plus

View full text Add to dashboard Cite

Biometric sensing technology has become a frequent element of everyday life as a result of the global demand for information security and safety legislation. In recent years, multimodal biometrics technology has become increasingly popular due to its ability to overcome the shortcomings of unimodal biometric systems. A hunger game search self-attention based Bi-LSTM model (HGSSA-Bi LSTM, Bi-directional long short-term memory) modal is presented in this paper for multimodal biometric identification. For removal of noise (unwanted) the pre-processing stage is used in the initial stage. An extended cascaded filter (ECF) is used with a combination of median and wiener filter in the pre-processing stage. Then, using the CNN model, feature extraction is utilized to extract features from the processed images. After feature extraction, fusing of feature is used with the aid of discriminant correlation analysis (DCA). Finally, the recognition process is performed by using the novel optimized HGSSA-Bi LSTM. The obtained outcome for the developed model is finally compared with other previous approaches such as CNN, RNN, DNN, and autoencoder models and the calculated performance based on accuracy 98.5%, precision 98%, F1-score 97.5%, sensitivity 98.5%, and specificity 99% accordingly.

show abstract

“…Secondly, if we consider the ageing assessment as a semi-supervised learning problem, we could use a Replicator Neural Networks (RNN) method on the cardiovascular signals. RNN is usually set up to perform anomaly detection in [29]: the RNN takes the raw signals as input and tries to reconstruct the input itself, as usually done in autoencoders [30]. In the present context, this would translate as follows: we train an RNN model on the "Historical" signals (normal case).…”

Section: Machine Learning Analysismentioning

confidence: 99%

Comparison of statistical, machine learning, and mathematical modelling methods to investigate the effect of ageing on dog’s cardiovascular system

Alizadeh,

Faya,

Liu

et al. 2023

ESAIM: ProcS

View full text Add to dashboard Cite

The aim of this work is to provide a preliminary comparison of different classes of methods to automatically detect the effect of ageing from in vivo data. The application which motivated this work is related to safety pharmacology, whose major goal is to determine, in a pre-clinical phase, whether a drug is potentially dangerous for the health. In particular, we are going to compare statistical, machine learning and mathematical modelling methods.

show abstract

Autoencoder Neural Networks for Outlier Correction in ECG- Based Biometric Identification

Cited by 17 publications

References 9 publications

English to Bangla Machine Translation Using Recurrent Neural Network

English to Bangla Machine Translation Using Recurrent Neural Network

HGSSA-bi LSTM: A Secure Multimodal Biometric Sensing Using Optimized Bi-Directional Long Short-Term Memory with Self-Attention

Comparison of statistical, machine learning, and mathematical modelling methods to investigate the effect of ageing on dog’s cardiovascular system

Contact Info

Product

Resources

About