This paper presents a novel, low-cost, portable impedance analyzer system designed for biopotential electrode evaluation and skin/electrode impedance measurement, critical for enhancing bioelectrical signal quality in healthcare applications. In contrast with conventional systems that depend on external PCs or host devices for data acquisition, visualization, and analysis, this design integrates all functionalities into a single, compact platform powered by the Analog Devices AD5933 impedance converter and a Raspberry Pi 4. The design incorporates custom analog circuitry to extend the measurement range from 10 Hz to 100 kHz and supports a wide impedance spectrum through switchable feedback resistors. Validated against a benchtop impedance analyzer, the system demonstrates high accuracy with normalized root-mean-square errors (NRMSEs) of 1.41% and 3.77% for the impedance magnitude and phase of passive components, respectively, and 1.43% and 1.29% for the biopotential electrode evaluation and skin/electrode impedance measurement. This cost-effective solution, with a total cost of USD 159, addresses the accessibility challenges faced by smaller research labs and healthcare facilities, offering a compact, low-power platform for reliable impedance analysis in biomedical applications.
31 January 2024 in Journal of Electronic Materials
Affective computing has emerged as a pivotal field in human–computer interaction. Recognizing human emotions through electroencephalogram (EEG) signals can advance our understanding of cognition and support healthcare. This study introduces a novel subject-independent emotion recognition framework by integrating multiple EEG emotion databases (DEAP, MAHNOB HCI-Tagging, DREAMER, AMIGOS and REFED) into a unified dataset. EEG segments were transformed into feature vectors capturing statistical, spectral, and entropy-based measures. Standardized pre-processing, analysis of variance (ANOVA) F-test feature selection, and six machine learning models were applied to the extracted features. Classification models such as Decision Tree, Discriminant Analysis, Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Naive Bayes, and Artificial Neural Networks (ANN) were considered. Experimental results demonstrate that SVM achieved the best performance for arousal classification (70.43%), while ANN achieved the highest accuracy for valence classification (68.07%), with both models exhibiting strong generalization across subjects. The results highlight the feasibility of developing biomimetic brain–computer interface (BCI) systems for objective assessment of emotional intelligence and its cognitive underpinnings, enabling scalable applications in affective computing and adaptive human–machine interaction.