RESUMO
Electrophysiological research has been widely utilized to study brain responses to acoustic stimuli. The frequency-following response (FFR), a non-invasive reflection of how the brain encodes acoustic stimuli, is a particularly propitious electrophysiologic measure. While the FFR has been studied extensively, there are limitations in obtaining and analyzing FFR recordings that recent machine learning algorithms may address. In this study, we aimed to investigate whether FFRs can be enhanced using an "improved" source-separation machine learning algorithm. For this study, we recruited 28 native speakers of American English with normal hearing. We obtained two separate FFRs from each participant while they listened to two stimulus tokens /i/ and /da/. Electroencephalographic signals were pre-processed and analyzed using a source-separation non-negative matrix factorization (SSNMF) machine learning algorithm. The algorithm was trained using individual, grand-averaged, or stimulus token spectrograms as a reference. A repeated measures analysis of variance revealed that FFRs were significantly enhanced (p < .001) when the "improved" SSNMF algorithm was trained using both individual and grand-averaged spectrograms, but not when utilizing the stimulus token spectrogram. Similar results were observed when extracting FFRs elicited by using either stimulus token, /i/ or /da/. This demonstration shows how the SSNMF machine learning algorithm, using individual and grand-averaged spectrograms as references in training the algorithm, significantly enhanced FFRs. This improvement has important implications for the obtainment and analytical processes of FFR, which may lead to advancements in clinical applications of FFR testing.
RESUMO
In this study, we explore the feasibility and performance of detecting scalp-recorded frequency-following responses (FFRs) with a specialized machine learning (ML) model. By leveraging the strengths of feature extraction of the source separation non-negative matrix factorization (SSNMF) algorithm and its adeptness in handling limited training data, we adapted the SSNMF algorithm into a specialized ML model with a hybrid architecture to enhance FFR detection amidst background noise. We recruited 40 adults with normal hearing and evoked their scalp recorded FFRs using the English vowel/i/with a rising pitch contour. The model was trained on FFR-present and FFR-absent conditions, and its performance was evaluated using sensitivity, specificity, efficiency, false-positive rate, and false-negative rate metrics. This study revealed that the specialized SSNMF model achieved heightened sensitivity, specificity, and efficiency in detecting FFRs as the number of recording sweeps increased. Sensitivity exceeded 80% at 500 sweeps and maintained over 89% from 1000 sweeps onwards. Similarly, specificity and efficiency also improved rapidly with increasing sweeps. The progressively enhanced sensitivity, specificity, and efficiency of this specialized ML model underscore its practicality and potential for broader applications. These findings have immediate implications for FFR research and clinical use, while paving the way for further advancements in the assessment of auditory processing.
Assuntos
Percepção da Fala , Adulto , Humanos , Percepção da Fala/fisiologia , Percepção Auditiva , Aprendizado de Máquina , Estimulação Acústica , EletroencefalografiaRESUMO
Source-Separation Non-Negative Matrix Factorization (SSNMF) is a mathematical algorithm recently developed to extract scalp-recorded frequency-following responses (FFRs) from noise. Despite its initial success, the effects of silent intervals on algorithm performance remain undetermined. Our purpose in this study was to determine the effects of silent intervals on the extraction of FFRs, which are electrophysiological responses that are commonly used to evaluate auditory processing and neuroplasticity in the human brain. We used an English vowel /i/ with a rising frequency contour to evoke FFRs in 23 normal-hearing adults. The stimulus had a duration of 150 ms, while the silent interval between the onset of one stimulus and the offset of the next one was also 150 ms. We computed FFR Enhancement and Noise Residue to estimate algorithm performance, while silent intervals were either included (i.e., the WithSI condition) or excluded (i.e., the WithoutSI condition) in our analysis. The FFR Enhancements and Noise Residues obtained in the WithoutSI condition were significantly better (p < .05) than those obtained in the WithSI condition. On average, the exclusion of silent intervals produced a 11.78% increment in FFR Enhancement and a 20.69% decrement in Noise Residue. These results not only quantify the effects of silent intervals on the extraction of human FFRs, but also provide recommendations for designing and improving the SSNMF algorithm in future research.
RESUMO
INTRODUCTION: Partial driving automation is not always reliable and requires that drivers maintain readiness to take over control and manually operate the vehicle. Little is known about differences in drivers' arousal and cognitive demands under partial automation and how it may make it difficult for drivers to transition from automated to manual modes. This research examined whether there are differences in drivers' arousal and cognitive demands during manual versus partial automation driving. METHOD: We compared arousal (using heart rate) and cognitive demands (using the root mean square of successive differences in normal heartbeats; RMSSD, and Detection Response Task; DRT) while 39 younger (M = 28.82 years) and 32 late-middle-aged (M = 52.72 years) participants drove four partially automated vehicles (Cadillac, Nissan Rogue, Tesla, and Volvo) on interstate highways. If compared to manual driving, drivers' arousal and cognitive demands were different under partial automation, then corresponding differences in heart rate, RMSSD, and DRT would be expected. Alternatively, if drivers' arousal and cognitive demands were similar in manual and partially automated driving, no difference in the two driving modes would be expected. RESULTS: Results suggest no significant differences in heart rate, RMSSD, or DRT reaction time performance between manual and partially automated modes of driving for either younger or late-middle-aged adults across the four test vehicles. A Bayes Factor analysis suggested that heart rate, RMSSD, and DRT data showed extreme evidence in favor of the null hypothesis. CONCLUSION: This novel study conducted on real roads with a representative sample provides important evidence of no difference in arousal and cognitive demands. Younger and late-middle-aged motorists who are new to partial automation are able to maintain arousal and cognitive demands comparable to manual driving while using the partially automated technology. Drivers who are more experienced with partially automated technology may respond differently than those with limited prior experience.