Automated seizure detection using limited-channel EEG and non-linear dimension reduction
… N T trees using all M spectral features extracted from all original P channels ( M = 5 × P ). …
split, first we selected mtry of the M original features ( mtry ≤ M ) at random as candidates for …
split, first we selected mtry of the M original features ( mtry ≤ M ) at random as candidates for …
An adaptive deep learning approach for PPG-based identification
Wearable biosensors have become increasingly popular in healthcare due to their
capabilities for low cost and long term biosignal monitoring. This paper presents a novel two-stage …
capabilities for low cost and long term biosignal monitoring. This paper presents a novel two-stage …
A non-EEG biosignals dataset for assessment and visualization of neurological status
Neurological assessment can be used to monitor a person's neurological status. In this
paper, we report collection and analysis of a multimodal dataset of Non-EEG physiological …
paper, we report collection and analysis of a multimodal dataset of Non-EEG physiological …
In-bed posture classification and limb identification
We propose an algorithm that uses pressure image data to detect a person's sleeping
posture and identifies different body limbs. Our algorithm can be used in monitoring bed-bound …
posture and identifies different body limbs. Our algorithm can be used in monitoring bed-bound …
A pressure map dataset for posture and subject analytics
MB Pouyan, J Birjandtalab… - 2017 IEEE EMBS …, 2017 - ieeexplore.ieee.org
Monitoring sleep postures can provide critical information when analyzing an individual's
sleep quality and in-bed behavior. Furthermore, tracking sleep posture over time can play an …
sleep quality and in-bed behavior. Furthermore, tracking sleep posture over time can play an …
Continuous eight-posture classification for bed-bound patients
MB Pouyan, S Ostadabbas, M Farshbaf… - 2013 6th …, 2013 - ieeexplore.ieee.org
… At the end of the training phase, we will have vectors S1 through SM for M posture classes.
In our work, each vector has size of N = 2048 bits and there are M = 8 postures and L = 20 …
In our work, each vector has size of N = 2048 bits and there are M = 8 postures and L = 20 …
Nonlinear dimension reduction for EEG-based epileptic seizure detection
Approximately 0.1 percent of epileptic patients die from unexpected deaths. In general, for
intractable seizures, it is crucial to have an algorithm to accurately and automatically detect …
intractable seizures, it is crucial to have an algorithm to accurately and automatically detect …
Random forest based similarity learning for single cell RNA sequencing data
… For each similarity matrix C i we then perform PCA, and again keep m i informative principal
components identified by the elbow method. This yields k matrices { F i ∈ ℝ n × m i } i = 1 k …
components identified by the elbow method. This yields k matrices { F i ∈ ℝ n × m i } i = 1 k …
Unsupervised EEG analysis for automated epileptic seizure detection
… Five normalized in-band power spectral density (NIPSD) features estimated for each of M
= … Javad Birjandtalab, Maziyar Baran Pouyan, and Mehrdad Nourani "Unsupervised EEG …
= … Javad Birjandtalab, Maziyar Baran Pouyan, and Mehrdad Nourani "Unsupervised EEG …
[HTML][HTML] A novel approach to predict sudden cardiac death (SCD) using nonlinear and time-frequency analyses from HRV signals
… (8)where n and m are the discrete time and frequency indexes, respectively, h(k) is the
frequency smoothing symmetric normed window of length 2N 1, g(p) is the time smoothing …
frequency smoothing symmetric normed window of length 2N 1, g(p) is the time smoothing …