Study of the Length of time Window in Emotion Recognition based on EEG Signals / Estudio de la Longitud de Ventana de Tiempo en el Reconocimiento de Emociones Basado en Señales EEG

Abstract The objective of this research is to present a comparative analysis using various lengths of time windows (TW) during emotion recognition, employing machine learning techniques and the portable wireless sensing device EPOC+. In this study, entropy will be utilized as a feature to evaluate the performance of different classifier models across various TW lengths, based on a dataset of EEG signals extracted from individuals during emotional stimulation. Two types of analyses were conducted: between-subjects and within-subjects. Performance measures such as accuracy, area under the curve, and Cohen's Kappa coefficient were compared among five supervised classifier models: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Decision Trees (DT). The results indicate that, in both analyses, all five models exhibit higher performance in TW ranging from 2 to 15 seconds, with the 10 seconds TW particularly standing out for between-subjects analysis and the 5-second TW for within-subjects; furthermore, TW exceeding 20 seconds are not recommended. These findings provide valuable guidance for selecting TW in EEG signal analysis when studying emotions.

Resumen El objetivo de esta investigación es presentar un análisis comparativo empleando diversas longitudes de ventanas de tiempo (VT) durante el reconocimiento de emociones, utilizando técnicas de aprendizaje automático y el dispositivo de sensado inalámbrico portátil EPOC+. En este estudio, se utilizará la entropía como característica para evaluar el rendimiento de diferentes modelos clasificadores en diferentes longitudes de VT, basándose en un conjunto de datos de señales EEG extraídas de individuos durante la estimulación de emociones. Se llevaron a cabo dos tipos de análisis: entre sujetos e intra-sujetos. Se compararon las medidas de rendimiento, tales como la exactitud, el área bajo la curva y el coeficiente de Cohen's Kappa, de cinco modelos clasificadores supervisados: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF) y Decision Trees (DT). Los resultados indican que, en ambos análisis, los cinco modelos presentan un mayor rendimiento en VT de 2 a 15 segundos, destacándose especialmente la VT de 10 segundos para el análisis entre los sujetos y 5 segundos intrasujetos; además, no se recomienda utilizar VT superiores a 20 segundos. Estos hallazgos ofrecen una orientación valiosa para la elección de las VT en el análisis de señales EEG al estudiar las emociones.

Thrombectomy for Anterior Circulation Stroke in a Witnessed Late Time Window Versus Early Time Window.

Introduction: Thrombectomy is the standard treatment for anterior circulation stroke due to large vessel occlusions in a late time window (6 to 24 hours) for patients selected based on perfusion imaging. Most patients treated in late time window studies presented as unwitnessed or wake-up strokes. Whether patients presenting with unwitnessed stroke have an actual time window greater than 6 hours is unclear. The aim of this study was to assess the outcomes of thrombectomy in the treatment of patients presenting with anterior circulation large vessel stroke in an actual late time window of more than 6 hours. Methods: This single-center registry of thrombectomy in the treatment of stroke caused by anterior circulation large vessel occlusions (LVOs) included 430 patients treated between 2011 and 2019. Patients were divided into 2 groups: an early time window (≤ 6 hours) group and a late time window group (> 6 hours). Results: Outcomes of the early and the late time window groups, respectively, were recanalization of 86.8% vs 82.7% (P = .29), symptomatic intracranial hemorrhage of 8.2% vs 5.7% (P = .40), good clinical outcome of 45.4% vs 41.3% (P = .46), and mortality of 20.2% vs 25% (P = .30) at 3 months. Conclusions: Thrombectomy for anterior circulation large vessel occlusions after 6 hours of symptoms onset seems to be as safe and effective as the standard thrombectomy within 6 hours from symptoms onset, even without perfusion analysis. Randomized trials are needed to confirm these findings.

Statistical analysis for efficacy of tirofiban combined with ozagrel in the treatment of progressive cerebral infarction patients out of thrombolytic therapy time window

OBJECTIVES: To investigate the safety and efficacy of combined tirofiban-ozagrel therapy for treating progressive stroke patients out of thrombolytic therapy time window. METHODS: This prospective, double-blind, randomized controlled study included 337 patients who had experienced an acute ischemic stroke between November 2017 and December 2018. All patients were randomized into three groups: 1) the tirofiban/ozagrel group (n=113), 2) the tirofiban group (n=110), and 3) the ozagrel group (n=114). The platelet aggregation (PAG), thrombin time (TT), prothrombin time (PT), activated partial thromboplastin time (APTT), and fibrinogen (FIB) levels in the patients from these groups were evaluated before starting treatment and then, at 24h, 7 days, and 14 days after treatment. The National Institutes of Health Stroke Scale (NIHSS) scores were evaluated before treatment and then, 24h, 1 week, 2 weeks, and 4 weeks after treatment. The Barthel Index (BI) score was used to measure safety, and the modified Rankin scale (mRS) was used to evaluate disability following 3 months of treatment. The risk factors affecting clinical outcomes were analyzed using logistic multivariate regression. RESULTS: The mean NIHSS score for all the patients was 13.17±3.13 before treatment, and no significant difference between the basic clinical parameters of the three patient groups was found. Following treatment, both PAG and FIB were significantly reduced compared with the baseline (p<0.05). The levels of PAG and FIB in the tirofiban/ozagrel group were significantly lower than those in the tirofiban and ozagrel groups at 24h and 7 days after treatment (p<0.05). The NIHSS score decreased significantly in all treatment groups (p<0.05). The tirofiban/ozagrel NIHSS scores were significantly lower than that of the tirofiban and ozagrel groups at 24h, 1 week, and 2 weeks post initiation (p<0.05 for all). There were no significant differences in the BI and mRS scores or the intracranial hemorrhage rates; further, age, sex, Trial of ORG 10172 in acute stroke treatment (TOAST) type, baseline NIHSS and 24-h NIHSS scores, baseline thrombus-related factors, and treatment methods were shown to not be independent risk factors for clinical outcomes. CONCLUSION: The combination of tirofiban and ozagrel, as well as monotherapy with either tirofiban or ozagrel, transiently improves the neural function of patients and reduces platelet aggregation and fibrinogen formation in the first 4 weeks following a stroke event; additionally, none of these treatments increased the risk for hemorrhage in these progressive stroke patients over a 3-month period.

Time-Resolved Spectroscopy of Ethanol Evaporation on Free-Standing Porous Silicon Photonic Microcavities.

In this work, we have followed ethanol evaporation at two different concentrations using a fiber optic spectrometer and a screen capture application with a resolving capacity of 10 ms. The transmission spectra are measured in the visible-near-infrared range with a resolution of 0.5 nm. Porous Silicon microcavities were fabricated by electrochemistry etching of crystalline silicon. The microcavities were designed to have a localized mode at 472 nm (blue band). Ethanol infiltration produces a redshift of approximately 17 nm. After a few minutes, a phase change from liquid to vapor occurs and the localized wavelength shifts back to the blue band. This process happens in a time window of only 60 ms. Our results indicate a difference between two distinct ethanol concentrations (70% and 35%). For the lower ethanol concentration, the blue shift rate process is slower in the first 30 ms and then it equals the high ethanol concentration blue shift rate. We have repeated the same process, but in an extended mode (750 nm), and have obtained similar results. Our results show that these photonic structures and with the spectroscopic technique used here can be implemented as a sensor with sufficient sensitivity and selectivity. Finally, since the photonic structure is a membrane, it can also be used as a transducer. For instance, by placing this photonic structure on top of a fast photodetector whose photo-response lies within the same bandwidth, the optical response can be transferred to an electrical signal.

Assessment of dose-effect and therapeutic time window in preclinical studies of rhEGF and GHRP-6 coadministration for stroke therapy.

BACKGROUND: Stroke continues to be a leading cause of mortality and morbidity worldwide, and novel therapeutic options for ischaemic stroke are urgently needed. In this context, drug combination therapies seem to be a viable approach, which has not been fully explored in preclinical studies. OBJECTIVES: In this work, we assessed the dose-response relationship and therapeutic time window, in global brain ischaemia, of a combined therapeutic approach of recombinant human epidermal growth factor (EGF) and growth hormone-releasing peptide-6 (GHRP-6). METHODS: Mongolian gerbils underwent 15 minutes occlusion of both common carotid arteries. Four different doses of rhEGF, GHRP-6 and these combined agents were intraperitoneally administered immediately after the onset of reperfusion. Having identified a better response with both agents, rhEGF+GHRP-6 were administered at 2, 4, 6, 8 or 24 hours after the onset of reperfusion to assess the time window of effectiveness. Animals were evaluated daily for neurological deficits. Three days post-occlusion, the animals were sacrificed and 2,3,5-triphenyltetrazolium chloride was used to quantify infarcted tissues. RESULTS: The coadministration of rhEGF and GHRP-6 at doses of 100 and 600 µg/kg, respectively, administered up to 4 hours following the ischaemic insult, significantly improved survival and neurological outcome, and reduced infarct volume compared with vehicle treatment. These results are considered as an additional proof of concept as supporting a combined therapeutic approach and justify the further development of this preclinical research.