scholarly journals Input level dependence of distortion products generated by saturating feedback in a cochlear model

2016 ◽  
Vol 37 (1) ◽  
pp. 1-9 ◽  
Author(s):  
Yasuki Murakami ◽  
Shunsuke Ishimitsu
Keyword(s):  
Cochlear Model ◽  
Distortion Products ◽  
Input Level

Including Physiologically Based Nonlinearity in a Cochlear Model

2010 ◽  
Vol 132 (2) ◽  
Author(s):  
Xiaoai Jiang ◽  
Karl Grosh
Keyword(s):  
Outer Hair Cell ◽  
Basilar Membrane ◽  
Fluid Model ◽  
Response Characteristic ◽  
Nonlinear Circuit ◽  
One Dimensional ◽  
Cochlear Model ◽  
Distortion Products ◽  
Voltage Dependent ◽  
Filtering Function

The outer hair cell (OHC) is known to be the main source of nonlinear activity in the cochlea. In this work, we used a one-dimensional fluid model of the cochlea coupled to a nonlinear model of the mechanical to electric coupling of the OHC and the basilar membrane (BM). The nonlinearity arises from the electromotility and the voltage-dependent stiffness of the OHC, and from the displacement dependence of the conductance of the stereocilia. We used a reciprocal nonlinear piezoelectric model of the OHC in combination with a model of stereocilia conductance depending on BM displacement (which resulted in a nonlinear circuit model). The mechanical properties of the various components of the model were motivated from physiological components of the cochlea. Simulations showed realistic gains in the activity, response saturation at high force level, and two-tone forcing generated distortion products while the shape of the filtering function was not as accurately replicated. We conclude that a cochlear model with a simple 1D fluid representation in combination with nonlinear OHC-stereocilia electromechanical response characteristic qualitatively predicts the compression property of the cochlea and can be used as a tool to investigate the relative importance of the various nonlinearities.

scholarly journals Learning Subject-Generalized Topographical EEG Embeddings Using Deep Variational Autoencoders and Domain-Adversarial Regularization

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1792
Author(s):  
Juan Hagad ◽  
Tsukasa Kimura ◽  
Ken-ichi Fukui ◽  
Masayuki Numao
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Emotion Classification ◽  
Limited Data ◽  
Neural Network Architecture ◽  
Building Models ◽  
The Subject ◽  
Data Constraints ◽  
Input Level ◽  
Normally Distributed

Two of the biggest challenges in building models for detecting emotions from electroencephalography (EEG) devices are the relatively small amount of labeled samples and the strong variability of signal feature distributions between different subjects. In this study, we propose a context-generalized model that tackles the data constraints and subject variability simultaneously using a deep neural network architecture optimized for normally distributed subject-independent feature embeddings. Variational autoencoders (VAEs) at the input level allow the lower feature layers of the model to be trained on both labeled and unlabeled samples, maximizing the use of the limited data resources. Meanwhile, variational regularization encourages the model to learn Gaussian-distributed feature embeddings, resulting in robustness to small dataset imbalances. Subject-adversarial regularization applied to the bi-lateral features further enforces subject-independence on the final feature embedding used for emotion classification. The results from subject-independent performance experiments on the SEED and DEAP EEG-emotion datasets show that our model generalizes better across subjects than other state-of-the-art feature embeddings when paired with deep learning classifiers. Furthermore, qualitative analysis of the embedding space reveals that our proposed subject-invariant bi-lateral variational domain adversarial neural network (BiVDANN) architecture may improve the subject-independent performance by discovering normally distributed features.

Cochlear origin of distortion products assessed by using 2 types of mutant mice

1991 ◽  
Vol 52 (1) ◽  
pp. 245-253 ◽  
Author(s):  
A. Schrott ◽  
J.-L Puel ◽  
G. Rebillard
Keyword(s):  
Mutant Mice ◽  
Distortion Products

scholarly journals Input-level-dependent approach to color error diffusion

2003 ◽  
Author(s):  
Vishal Monga ◽  
Niranjan Damera-Venkata ◽  
Brian L. Evans
Keyword(s):  
Error Diffusion ◽  
Color Error ◽  
Input Level

scholarly journals Handling missing MRI sequences in deep learning segmentation of brain metastases: a multicenter study

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Endre Grøvik ◽  
Darvin Yi ◽  
Michael Iv ◽  
Elizabeth Tong ◽  
Line Brennhaug Nilsen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Brain Metastases ◽  
Multicenter Study ◽  
Roc Curve ◽  
Inversion Recovery ◽  
Fast Spin Echo ◽  
Operating Characteristics ◽  
Test Set ◽  
Mri Sequences ◽  
Input Level

AbstractThe purpose of this study was to assess the clinical value of a deep learning (DL) model for automatic detection and segmentation of brain metastases, in which a neural network is trained on four distinct MRI sequences using an input-level dropout layer, thus simulating the scenario of missing MRI sequences by training on the full set and all possible subsets of the input data. This retrospective, multicenter study, evaluated 165 patients with brain metastases. The proposed input-level dropout (ILD) model was trained on multisequence MRI from 100 patients and validated/tested on 10/55 patients, in which the test set was missing one of the four MRI sequences used for training. The segmentation results were compared with the performance of a state-of-the-art DeepLab V3 model. The MR sequences in the training set included pre-gadolinium and post-gadolinium (Gd) T1-weighted 3D fast spin echo, post-Gd T1-weighted inversion recovery (IR) prepped fast spoiled gradient echo, and 3D fluid attenuated inversion recovery (FLAIR), whereas the test set did not include the IR prepped image-series. The ground truth segmentations were established by experienced neuroradiologists. The results were evaluated using precision, recall, Intersection over union (IoU)-score and Dice score, and receiver operating characteristics (ROC) curve statistics, while the Wilcoxon rank sum test was used to compare the performance of the two neural networks. The area under the ROC curve (AUC), averaged across all test cases, was 0.989 ± 0.029 for the ILD-model and 0.989 ± 0.023 for the DeepLab V3 model (p = 0.62). The ILD-model showed a significantly higher Dice score (0.795 ± 0.104 vs. 0.774 ± 0.104, p = 0.017), and IoU-score (0.561 ± 0.225 vs. 0.492 ± 0.186, p < 0.001) compared to the DeepLab V3 model, and a significantly lower average false positive rate of 3.6/patient vs. 7.0/patient (p < 0.001) using a 10 mm3 lesion-size limit. The ILD-model, trained on all possible combinations of four MRI sequences, may facilitate accurate detection and segmentation of brain metastases on a multicenter basis, even when the test cohort is missing input MRI sequences.

Sign in / Sign up

Export Citation Format

Share Document