Despite the growing interest in the use of electroencephalogram (EEG) signals as a potential biometric for subject identification and the recent advances in the use of deep learning (DL) models to study neurological signals, such as electrocardiogram (ECG), electroencephalogram (EEG), electroretinogram (ERG), and electromyogram (EMG), there has been a lack of exploration in the use of state-of-the-art DL models for EEG-based subject identification tasks owing to the high variability in EEG features across sessions for an individual subject. In this paper, we explore the use of state-of-the-art DL models such as ResNet, Inception, and EEGNet to realize EEG-based biometrics on the BED dataset, which contains EEG recordings from 21 individuals. We obtain promising results with an accuracy of 63.21%, 70.18%, and 86.74% for Resnet, Inception, and EEGNet, respectively, while the previous best effort reported accuracy of 83.51%. We also demonstrate the capabilities of these models to perform EEG biometric tasks in real-time by developing a portable, low-cost, real-time Raspberry Pi-based system that integrates all the necessary steps of subject identification from the acquisition of the EEG signals to the prediction of identity while other existing systems incorporate only parts of the whole system.

This work investigates the use of external voltage resets to reduce drifting issues of iridium oxide (IrOx) pH sensing films. Two types of IrOx films prepared by sol–gel and electroplating techniques were examined comparing hydrous and anhydrous material characteristics. The thin-film IrO _x allows inexpensive processing for flexible polyimide substrates enabling planar and monolithic integration for wearables and miniature pH sensors. Open circuit potential drifts and external voltage resets were investigated for freshly prepared electrodes and re-tested after 14 days. External resets were examined at different voltage levels. Sol–gel electrodes showed 57% and 81% drift improvement in acid and alkaline test solutions, respectively, while electroplated ones showed 84% and 88% improvements. Sensitivity and hysteresis were investigated after external resets and showed promising results. A total of 15 sol–gel and 15 electroplated electrodes were characterized. Differences in pH characteristics are attributed to different types of IrO _x composition. The quicker response transitions and reduced potential drifts will enable reliable long-term pH monitoring and reduce frequent calibration for pH-sensing applications.

Electrodeposited iridium oxide (IrOx) pH sensors are gaining interest in numerous biomedical applications, attributed to their superior accuracy, straightforward fabrication, and compatibility with other microfabrication processes. However, the pH sensing range and stability of these sensors have been long-entrenched challenges to control. In this study, we explored the sensor’s behavior under pH conditions beyond its typical sensing range, unearthing potential correlations between the sensing range and other influential factors. Based on these findings, we proposed and implemented a practical method to manipulate the sensing range to designated pH regions. This methodology significantly expanded the sensor’s applicability to encompass extreme acidic or basic environments. A series of investigations revealed that, under such severe conditions, the sensor’s stability—as quantified by drift—could be enhanced more than tenfold posttreatment. Moreover, other stability metrics, including linearity and hysteresis, exhibited notable improvements through this technique, as validated by titration tests in the extended pH sensing ranges. This research offers meaningful insights and a promising approach to enhance the sensing range and stability of electrodeposited IrOx pH sensors, thereby potentially progressing their practical application in biomedical domains.