Hybrid 3DCNN-RBM Network for Gas Mixture Concentration Estimation With Sensor Array

Pareek, Vishakha; Chaudhury, Santanu; Singh, Sanjay

doi:10.1109/jsen.2021.3105414

Cited by 12 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effectiveness of the developed arrhythmia classification approach was analyzed with the previously utilized detection models and heuristic algorithms to validate the effectiveness. Heuristic algorithms used for these analysis were Single Static Assignment (SSA) [30], Coyote Optimization Algorithm (COA) [31], ASO [27], and DSO [26], while the classification techniques used for this performance analysis was SVM [8], 3DCNN [28], LSTM [6] and 3DCNN-ResNet [29].…”

Section: Methodsmentioning

confidence: 99%

Enhanced Arrhythmia Classification System From Ecg Signals via Hybrid Optimization-Based Improved 3dcnn-Resnet

Munawar¹,

Geetha²,

Srinvas³

2023

INDJCSE

View full text Add to dashboard Cite

Arrhythmia is characterized by aberrant electrical activity of the heart, which can be identified the changes in the Electrocardiogram (ECG). Automatic ECG detection is needed because it is mainly used for detecting arrhythmias. Although several algorithms are implemented for the automatic classification of cardiac arrhythmias based on the characteristics of the ECG, their stratification rate is very less because of the unreliable features of signal characteristics or limited generalization capability of the classifier and it is still difficult to diagnose the arrhythmia disease automatically. At this work, they propose a new hybrid deep learning technique for the classification of arrhythmia from the ECG signal. Initially, the wanted ECG signal is collected from the standard websites and then it is assigned to the preprocessing technique. The preprocessing techniques includes the artifacts removal and peak detection techniques noise removal for the elimination of the unwanted distortions and the noise present in the signal then the resultant signal is fed to the Short-time Fourier transform (STFT) to achieve the spectrogram signals and then the spectrogram signal. Thus, the resultant spectrogram signal is given to the hybrid deep learning architecture that includes the 3DCNN-ResNet for diagnosing the arrhythmia disease. Here, the parameter optimizations take place using the hybrid Artificial Showering Dolphin Swarm Optimization (ASDSO) to increase the classification performance. It classifies the signal into five prominent classes that is Premature Ventricular Contraction (V), Right Bundle Branch Block (RBBB or R), Normal Sinus Rhythm (N), Left Bundle Branch Block (LBBB or L), and Atrial Premature Beat (A). The success of the proposed model is validated through diverse benchmark datasets with the performance validation like recall, precision, accuracy, f-measure and some negative measures.

show abstract

Section: Methodsmentioning

confidence: 99%

Enhanced Arrhythmia Classification System From Ecg Signals via Hybrid Optimization-Based Improved 3dcnn-Resnet

Munawar¹,

Geetha²,

Srinvas³

2023

INDJCSE

View full text Add to dashboard Cite

show abstract

“…Adaptive drift correction, which is a method that updates a classifier continuously using new samples, has been implemented in various deep learning structures [5]. Fine-tuning has also been carried out for novel deep learning models such as autoencoders [12], restricted Boltzmann machines [13], deep belief networks [14], and augmented convolutional neural networks [15]. Furthermore, online drift compensation methods, which can update trained models with new samples, have been studied.…”

Section: Introductionmentioning

confidence: 99%

A Sensor Drift Compensation Method with a Masked Autoencoder Module

Kwon,

Park,

Jang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Deep learning algorithms are widely used for pattern recognition in electronic noses, which are sensor arrays for gas mixtures. One of the challenges of using electronic noses is sensor drift, which can degrade the accuracy of the system over time, even if it is initially trained to accurately estimate concentrations from sensor data. In this paper, an effective drift compensation method is introduced that adds sensor drift information during training of a neural network that estimates gas concentrations. This is achieved by concatenating a calibration feature vector with sensor data and using this as an input to the neural network. The calibration feature vector is generated via a masked-autoencoder-based feature extractor trained with transfer samples, and acts as a prompt to convey sensor drift information. Our method is tested on a 3-year gas sensor array drift dataset, showing that a neural network using our method performs better than other models, including a network with additional fine tuning, demonstrating that our method is efficient at compensating for sensor drift. In this study, the effectiveness of using prompts for network training is confirmed, which better compensates for drifts in new sensor signals than network fine-tuning.

show abstract

“…The emergence of convolutional neural networks (CNNs) has brought the performance of the EN system to a higher level. Many CNN models, such as residual neural network (ResNet) and visual geometry group (VGG) network, have been employed to identify gas categories and to estimate gas concentrations [28], [29], [30]. While CNN improves the accuracy of gas classification, it also comes across some important challenges.…”

Section: Introductionmentioning

confidence: 99%

E-Nose System Based on Fourier Series for Gases Identification and Concentration Estimation From Food Spoilage

Luo

Zhu

et al. 2023

IEEE Sensors J.

View full text Add to dashboard Cite

This work presents an electronic nose (EN)-based gas identification and concentration estimation method for the detection of food spoilage. The response data of sensors were acquired through a commercial gas sensor array and data acquisition circuit board and transformed into pictures with the form of the Fourier series. A convolutional neural network (CNN) model was used to identify the pictures from the conversion of sensor data, thus achieving the purpose of identifying the gases (C 2 H 5 OH, NH 3 , and H 2 S). In order to solve the problem of sample imbalance and to improve the generalization performance of classification models, the synthetic minority oversampling technique (SMOTE) and dropout technique were employed. Fivefold cross-validation was used to evaluate the performance of the model, of which the gas identification accuracy rate reached 96.67%. Moreover, a gas concentration regression model with the advantages of simplicity and strong interpretability was further proposed to estimate the concentrations of C 2 H 5 OH, NH 3 , and H 2 S. The mean absolute errors and coefficients of determination for the concentration estimation of C 2 H 5 OH, NH 3 , and H 2 S are (3.71 ppm, 0.968), (0.50 ppm, 0.968), and (0.13 ppm, 0.99), respectively. Furthermore, we used our model to evaluate the freshness of kiwifruit, pork, and beef, and it showed satisfactory predictive performance. The method proposed in this work realizes high-precision detection of gases from food spoilage and has a good application prospect in the rapid judgment of food freshness on the EN system.

show abstract

Hybrid 3DCNN-RBM Network for Gas Mixture Concentration Estimation With Sensor Array

Cited by 12 publications

References 43 publications

Enhanced Arrhythmia Classification System From Ecg Signals via Hybrid Optimization-Based Improved 3dcnn-Resnet

Enhanced Arrhythmia Classification System From Ecg Signals via Hybrid Optimization-Based Improved 3dcnn-Resnet

A Sensor Drift Compensation Method with a Masked Autoencoder Module

E-Nose System Based on Fourier Series for Gases Identification and Concentration Estimation From Food Spoilage

Contact Info

Product

Resources

About