Multiple Temporal Windows Research Articles

Patient-specific method for predicting epileptic seizures based on DRSN-GRU

Epilepsy is one of the most common neurological disorders worldwide and can cause the brain to stop working properly or even endanger the life of the patient. Epilepsy prediction is a prerequisite for seizure control, allowing preventive measures to mitigate damage or control seizures. It has been found that abnormal brain activity begins some time before a seizure, which is known as the pre-ictal state. In this study, we reconsidered the temporal scope of the pre-ictal period and divided it into multiple temporal windows. A patient-specific seizure prediction method based on deep residual shrinkage network (DRSN) and gated recurrent unit (GRU) was then proposed. The temporal dependency of the signal of different time windows in the pre-ictal period is modeled by introducing GRU into a DRSN. In addition, automatic feature extraction is achieved by applying soft threshold denoising and attention mechanism inside the neural network. The proposed method was tested on four patients reasonably selected from the CHB-MIT scalp EEG dataset, which achieved a sensitivity of 90.54%, an AUC value of 0.88, and a false prediction rate of 0.11/h. The results obtained by our method are compared with the recent epilepsy prediction methods. Compared with the being among the best method, our method still has a little gap, but it also shows a new idea and some advantages.

A Spatiotemporal Brain Network Analysis of Alzheimer's Disease Based on Persistent Homology.

Current brain network studies based on persistent homology mainly focus on the spatial evolution over multiple spatial scales, and there is little research on the evolution of a spatiotemporal brain network of Alzheimer’s disease (AD). This paper proposed a persistent homology-based method by combining multiple temporal windows and spatial scales to study the spatiotemporal evolution of brain functional networks. Specifically, a time-sliding window method was performed to establish a spatiotemporal network, and the persistent homology-based features of such a network were obtained. We evaluated our proposed method using the resting-state functional MRI (rs-fMRI) data set from Alzheimer’s Disease Neuroimaging Initiative (ADNI) with 31 patients with AD and 37 normal controls (NCs). In the statistical analysis experiment, most network properties showed a better statistical power in spatiotemporal networks than in spatial networks. Moreover, compared to the standard graph theory properties in spatiotemporal networks, the persistent homology-based features detected more significant differences between the groups. In the clustering experiment, the brain networks on the sliding windows of all subjects were clustered into two highly structured connection states. Compared to the NC group, the AD group showed a longer residence time and a higher window ratio in a weak connection state, which may be because patients with AD have not established a firm connection. In summary, we constructed a spatiotemporal brain network containing more detailed information, and the dynamic spatiotemporal brain network analysis method based on persistent homology provides stronger adaptability and robustness in revealing the abnormalities of the functional organization of patients with AD.

Modelling the Relationship between Rainfall and Mental Health Using Different Spatial and Temporal Units.

Drought is thought to impact upon the mental health of agricultural communities, but studies of this relationship have reported inconsistent results. A source of inconsistency could be the aggregation of data by a single spatiotemporal unit of analysis, which induces the modifiable areal and temporal unit problems. To investigate this, mental health-related emergency department (MHED) presentations among residents of the Wheat Belt region of Western Australia, between 2002 and 2017, were examined. Average daily rainfall was used as a measure of drought. Associations between MHED presentations and rainfall were estimated based on various spatial aggregations of underlying data, at multiple temporal windows. Wide variation amongst results was observed. Despite this, two key features were found: Associations between MHED presentations and rainfall were generally positive when rainfall was measured in summer months (rate ratios up to 1.05 per 0.5 mm of daily rainfall) and generally negative when rainfall was measured in winter months (rate ratios as low as 0.96 per 0.5 mm of daily rainfall). These results demonstrate that the association between drought and mental health is quantifiable; however, the effect size is small and varies depending on the spatial and temporal arrangement of the underlying data. To improve understanding of this association, more studies should be undertaken with longer time spans and examining specific mental health outcomes, using a wide variety of spatiotemporal units.

A New Architecture Based on IoT and Machine Learning Paradigms in Photovoltaic Systems to Nowcast Output Energy.

The classic models used to predict the behavior of photovoltaic systems, which are based on the physical process of the solar cell, are limited to defining the analytical equation to obtain its electrical parameter. In this paper, we evaluate several machine learning models to nowcast the behavior and energy production of a photovoltaic (PV) system in conjunction with ambient data provided by IoT environmental devices. We have evaluated the estimation of output power generation by human-crafted features with multiple temporal windows and deep learning approaches to obtain comparative results regarding the analytical models of PV systems in terms of error metrics and learning time. The ambient data and ground truth of energy production have been collected in a photovoltaic system with IoT capabilities developed within the Opera Digital Platform under the UniVer Project, which has been deployed for 20 years in the Campus of the University of Jaén (Spain). Machine learning models offer improved results compared with the state-of-the-art analytical model, with significant differences in learning time and performance. The use of multiple temporal windows is shown as a suitable tool for modeling temporal features to improve performance.

Non-stationary Group-Level Connectivity Analysis for Enhanced Interpretability of Oddball Tasks.

Neural responses of oddball tasks can be used as a physiological biomarker to evaluate the brain potential of information processing under the assumption that the differential contribution of deviant stimuli can be assessed accurately. Nevertheless, the non-stationarity of neural activity causes the brain networks to fluctuate hugely in time, deteriorating the estimation of pairwise synergies. To deal with the time variability of neural responses, we have developed a piecewise multi-subject analysis that is applied over a set of time intervals within the stationary assumption holds. To segment the whole stimulus-locked epoch into multiple temporal windows, we experimented with two approaches for piecewise segmentation of EEG recordings: a fixed time-window, at which the estimates of FC measures fulfill a given confidence level, and variable time-window, which is segmented at the change points of the time-varying classifier performance. Employing the weighted Phase Lock Index as a functional connectivity metric, we have presented the validation in a real-world EEG data, proving the effectiveness of variable time segmentation for connectivity extraction when combined with a supervised thresholding approach. Consequently, we performed a piecewise group-level analysis of electroencephalographic data that deals with non-stationary functional connectivity measures, evaluating more carefully the contribution of a link node-set in discriminating between the labeled oddball responses.

A penalized time-frequency band feature selection and classification procedure for improved motor intention decoding in multichannel EEG

Objective. Motor imagery brain–computer interfaces (MI-BCIs) based on electroencephalography (EEG), a promising technology to provide assistance and support rehabilitation of neurological patients with sensorimotor impairments, require a reliable and adaptable subject-specific model to efficiently decode motor intention. The most popular EEG feature extraction algorithm for MI-BCIs is the common spatial patterns (CSP) method, but its performance strongly depends on the predefined frequency band and time segment length for analyzing the EEG signal. Approach. In this work, a novel method for efficiently decoding motor intention for EEG-based BCIs performing multiple frequency band analysis in multiple EEG segments is presented. This decoding algorithm uses raw multichannel EEG data which are decomposed into specific temporal and frequency bands. Features are extracted at each - band by using CSP. Feature selection and classification are simultaneously performed by means of a fast procedure, based on elastic-net regression, which allows for the inclusion of a priori discriminative information into the model. The effectiveness of the proposed method is tested off-line on two public EEG-based MI-BCI datasets and on a self-acquired dataset in two configurations: multiple temporal windows and single temporal window. Main results. The experimental results show that the proposed multiple time-frequency band method yields overall accuracy improvements of up to (average accuracy of 84.8%) as compared to the best current state-of-the-art methods based on filter bank analysis and CSP for MI detection. Also, classification variability is reduced, making the proposed method more robust to intra-subject EEG fluctuations. Significance. This paper presents a novel approach for improving motor intention detection by automatically selecting subject-specific spatio-temporal-spectral features, especially when MI has to be detected against rest condition. This technique contributes to the further advancement and application of EEG-based MI-BCIs for assistance and neurorehabilitation therapy.

Ensemble classifier of long short-term memory with fuzzy temporal windows on binary sensors for activity recognition

There are approaches that successfully recognize activities of daily living by using a trained classifier on feature vectors created from binary sensor data. Although these approaches have been successful, there are still open issues such as the evaluation of multiple temporal windows, ensembles of classifiers or unbalanced classes which need to be addressed in order to improve the performance of the real-time activity recognition process. In this paper, we present a methodology for Real-Time Activity Recognition based on the diverse fields of Machine Learning, including Fuzzy Logic and Recurrent Neural Networks. The methodology uses a long-term and short-term representation of binary-sensor activations based on Fuzzy Temporal Windows. The paper proposes an ensemble of activity-based classifiers for the purposes of balanced training, where each classifier in the ensemble is a Long Short-Term Memory. The approach was evaluated using two binary-sensor datasets of daily living activities and benchmarked against previous approaches based on the combination of sensor activation features.

Evaluation of long-term trends in extreme precipitation: Implications of in-filled historical data use for analysis

This study focuses on the assessment of biases from infilling missing precipitation data on the detection of long-term change using parametric and non-parametric statistical techniques. Long-term historical precipitation data available for almost 100years at 53 rain gages in south Florida, USA, with gages having varying lengths of missing data are used for the study. Precipitation data with gaps and time series with spatial interpolated data are analyzed. Chronologically complete datasets are often used in climate variability studies by analyzing data in multiple temporal windows. The temporal windows selected in this work coincide with Atlantic multi-decadal oscillation (AMO) cool and warm phases that strongly influence precipitation extremes and characteristics in the study region. Selection of these windows has helped in evaluating the extremes derived based on infilled and unfilled data. The frequency of occurrence of precipitation extremes over a pre-specified threshold is also analyzed. Results indicate that infilled precipitation data introduce large biases in the statistical trends and over and under-estimate low and high extremes respectively. Evaluation of three extreme precipitation indices (i.e. Rx1day, R25mm and R50mm) indicates that bias increases with increase in amount of missing data. Nonparametric hypothesis tests indicate that statistical distributions of data of infilled and unfilled data are different when the data infilled is more than 5% of the entire data. Infilled data also introduced high variability in precipitation extremes in AMO cool and warm phases along with the changes in the frequency of occurrence of extreme events over a threshold.

Variation in Timing of Planting Influences Bluebunch Wheatgrass Demography in an Arid System

Establishing perennial grasses from seed in postdisturbance Wyoming big sagebrush (Artemesia tridentata subsp. wyomingensis Welsh) communities is often unsuccessful, due in part to a lack of knowledge of the seedling ecology of perennial grasses. We examined the influence of planting timing on germination and seedling demography of bluebunch wheatgrass (Pseudoroegneria spicata [Pursh] A. Love) in the northern Great Basin. In 2008 (year 1) and 2009 (year 2) we planted seeds monthly, September–December, in 1-m2 plots (500 seeds per plot) using a randomized block design with five replications. Germination timing was indexed using seed bags placed adjacent to 1-m2 plots and retrieved at 2-wk intervals in fall and 1-mo intervals in spring. Seedlings were marked in March–June of the year following planting; seedlings alive in July were considered initially established. Planting in September and October had up to 80% germination prior to winter, whereas December plantings germinated mainly in spring and at reduced rates (15–35%). Seeds planted in September and October emerged approximately a month earlier than November–December plantings. The percentage of germinated seeds that emerged was highest for September–October plantings but the percentage of emergent seeds surviving to the end of the first growing season was highest for later plantings. Final seedling density was lowest for November planting in year 1 and highest for September and October planting in year 2. Our data indicate that timing of and performance at critical stages of seedling development were affected by planting month. We suggest that it may be possible to use emerging technologies (e.g., seed coatings or germplasm manipulations) to produce variable chronologies of seedling development with single plantings and allow managers to exploit multiple temporal windows of opportunity for seedling establishment.

Dual Regulation of Anterograde and Retrograde Transmission by Endocannabinoids

Endocannabinoids (eCBs) are feedback messengers in the nervous system that act at the presynaptic nerve terminal to inhibit transmitter release. Here we report that in brain slices from rat, eCBs are released from vasopressin (VP) neurons in the paraventricular nucleus of the hypothalamus following coincident bursts of presynaptic and postsynaptic spiking. eCBs transiently depress glutamate release from excitatory terminals and, in doing so, prevent the synapses from undergoing long-term depression (LTD). Specifically, we show that blockade of CB1 receptors unmasks LTD following coincident presynaptic and postsynaptic activity. This LTD is presynaptic in nature, but requires the release of the opioid peptide dynorphin from the postsynaptic neuron. Dynorphin release and subsequent LTD require the activation of postsynaptic metabotropic glutamate receptors (mGluRs). Our findings indicate that eCBs, by transiently depressing glutamate release, limit mGluR activation and indirectly gate release of dynorphin from the postsynaptic neuron. We propose that eCBs, in addition to their well described role in the rapid modulation of transmitter release from the nerve terminal, also regulate the release of other retrograde transmitters and thus encode for multiple temporal windows of synaptic plasticity.