Blind Music Timbre Source Isolation by Multi- resolution Comparison of Spectrum Signatures

Zhang, Xin; Jiang, Wenxin; Raś, Zbigniew W.; Lewis, Rory

doi:10.1007/978-3-642-13529-3_65

Cited by 4 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 Moreover, neurological pathological activity may manifest itself differently from animal to animal or individual to individual. 5,6 Because of this, it is necessary to not only collect large distributions of data sets in order for a machine to learn, but also a unique set of classification rules for each individual. Given the difficulty of obtaining human EEG data 7 of continuous artifact or pathological states, this can be impractical.…”

Section: Introductionmentioning

confidence: 99%

Investigation into the efficacy of generating synthetic pathological oscillations for domain adaptation

et al. 2013

Self Cite

View full text Add to dashboard Cite

In our ongoing work to integrate Knowledge Discovery in Databases (KDD) into neuroscience, we present a paper that facilitates overcoming the two challenges preventing this integration. Pathological oscillations found in the human brain are difficult to evaluate because 1) there is often no time to learn and train off of the same distribution in the fatally sick, and 2) sinusoidal signals found in the human brain are complex and transient in nature, requiring large data sets to work with which are costly and often very expensive or impossible to acquire. Overcoming these challenges in today's neuro-intensive care unit (ICU) requires insurmountable resources. For these reasons, optimizing KDD for pathological oscillations so machine learning systems can predict neuropathological states would be of immense value. Domain adaptation, which allows a way of predicting on a separate set of data than the training data, can theoretically overcome the first challenge. However, the challenge of acquiring large data sets that show whether domain adaptation is a good candidate to test in a live neuro ICU remains a challenge. To solve this conundrum, we present a methodology for generating synthesized neuropathological oscillations for domain adaptation.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigation into the efficacy of generating synthetic pathological oscillations for domain adaptation

et al. 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, neurological pathological activity may manifest itself differently from animal to animal or individual to individual [17] [7]. In a healthy human brain there is a precise interaction of neural activities, but when one develops a neurological illness (pathology) this synchronization breaks down.…”

Section: Introductionmentioning

confidence: 99%

Classification of Epileptoid Oscillations in EEG Using Shannon’s Entropy Amplitude Probability Distribution

Broberg

Lewis

2014

Similarity Search and Applications

Self Cite

View full text Add to dashboard Cite

Abstract. This paper presents an additional tool the authors have developed to continue merging the fields of computational neuroscience with medical based neurodiagnostic clinical research, particularly those associated with machine learning in Big Electroencephalogram (EEG) Data. The authors introduce a means to identify various types of epileptic pathologic oscillations using a parameter based on the Shannon entropy of the probability distribution of the amplitudes within EEG signals. Multiple entropy and entropy-like measures have been explored to aid in epileptic seizure classification including Kolmogorov-Sinai entropy, spectral entropy, Renyi entropy, approximate entropy, and equal frequency discretization. Here we propose a more computational efficient measure which calculates a discrete probability distribution directly from the recorded amplitudes of an EEG recording over a specified window and uses an entropy-like calculation to reduce dimensionality.

show abstract

Supervised Learning for the Neurosurgery Intensive Care Unit Using Single-Layer Perceptron Classifiers

Mello

Lewis

Brooks‐Kayal

et al. 2014

Brain Informatics and Health

View full text Add to dashboard Cite

Blind Music Timbre Source Isolation by Multi- resolution Comparison of Spectrum Signatures

Cited by 4 publications

References 13 publications

Investigation into the efficacy of generating synthetic pathological oscillations for domain adaptation

Investigation into the efficacy of generating synthetic pathological oscillations for domain adaptation

Classification of Epileptoid Oscillations in EEG Using Shannon’s Entropy Amplitude Probability Distribution

Supervised Learning for the Neurosurgery Intensive Care Unit Using Single-Layer Perceptron Classifiers

Contact Info

Product

Resources

About