Answers are grounded in this paper and cite their sources.
Demonstrates an inverter-based operational transconductance amplifier paired with hybrid deep learning models for arrhythmia detection, indicating high diagnostic accuracy up to 99.12%.
In this study, an inverter‐based operational transconductance amplifier (OTA) is designed using various configurations of FinFET and CNTFET technologies. The performance parameters of the OTA, including gain, power consumption, bandwidth, and output resistance, are analysed with variations in CNT parameters. Furthermore, the inverter‐based OTA is utilised as the core amplifier in a chopper‐stabilised amplifier. Three novel configurations of tunable pseudoresistors are employed as feedback resistors in the chopper‐stabilized amplifier, and their impact on OTA performance is evaluated. Additionally, a machine learning‐based model for arrhythmia diagnosis is developed. Algorithms such as ANN+LSTM, CNN+LSTM, and RNN+LSTM are implemented, and their performance is assessed based on training accuracy, training loss, and a confusion matrix to highlight their effectiveness. Training accuracy for ANN+LSTM, CNN+LSTM and RNN+LSTM is found to be 96.56%, 99.12%, and 94.56%, respectively.
No takes yet. Share an insight, caveat, or question.
Farshori et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: