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.

scholarly journals Automatic Parking Controller with a Twin Artificial Neural Network Architecture

2019 ◽  
Vol 2019 ◽  
pp. 1-18 ◽  
Author(s):  
Jaeyoung Moon ◽  
Il Bae ◽  
Shiho Kim
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Neural Network Architecture ◽  
Control Laws ◽  
Confined Spaces ◽  
Human Driver ◽  
Kinematic Models ◽  
Automatic Parking ◽  
The Subject ◽  
Traditional Approaches

We propose an artificial deep neural network- (ANN-) based automatic parking controller that overcomes a stubborn restriction prevalent in traditional approaches. The proposed ANN learns human-like control laws for automatic parking through supervised learning from a training database generated by computer-aided optimizations or real experiments. By learning the relationships between the instantaneous vehicle states and the corresponding maneuver parameters, the proposed twin controller yields lateral and longitudinal maneuvering parameters for executing automatic parking tasks in confined spaces. The proposed automatic parking controller exhibits a twin architecture comprising a main agent and its cloned agent. Before the main agent assumes a maneuvering action, the cloned agent predicts the consequences of the maneuvering action through a Collision Checking and Adjustment (CCA) system. The proposed parking agent operates like a human driver in a manner that is characterized by an unplanned trajectory. In addition, the kinematics of the subject vehicle is not exactly modelled for parking control. The simulation results demonstrate that the proposed twin agent emulates the attributes of a human driver such as adaptive control and determines the consequences of the tentative maneuvering action under varying kinematic models of the subject vehicle. We validate the proposed parking controller by simulating the software-in-the-loop architecture using a PreScan simulator in which the dynamics of the virtual vehicle’s behavior resemble a real vehicle.

scholarly journals Bioacoustic classification of avian calls from raw sound waveforms with an open-source deep learning architecture

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Francisco J. Bravo Sanchez ◽  
Md Rahat Hossain ◽  
Nathan B. English ◽  
Steven T. Moore
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Limited Data ◽  
Extraction Techniques ◽  
Neural Network Architecture ◽  
The Neural Network ◽  
Current Classification ◽  
Efficient Learning ◽  
Sound Features

AbstractThe use of autonomous recordings of animal sounds to detect species is a popular conservation tool, constantly improving in fidelity as audio hardware and software evolves. Current classification algorithms utilise sound features extracted from the recording rather than the sound itself, with varying degrees of success. Neural networks that learn directly from the raw sound waveforms have been implemented in human speech recognition but the requirements of detailed labelled data have limited their use in bioacoustics. Here we test SincNet, an efficient neural network architecture that learns from the raw waveform using sinc-based filters. Results using an off-the-shelf implementation of SincNet on a publicly available bird sound dataset (NIPS4Bplus) show that the neural network rapidly converged reaching accuracies of over 65% with limited data. Their performance is comparable with traditional methods after hyperparameter tuning but they are more efficient. Learning directly from the raw waveform allows the algorithm to select automatically those elements of the sound that are best suited for the task, bypassing the onerous task of selecting feature extraction techniques and reducing possible biases. We use publicly released code and datasets to encourage others to replicate our results and to apply SincNet to their own datasets; and we review possible enhancements in the hope that algorithms that learn from the raw waveform will become useful bioacoustic tools.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Sign in / Sign up

Export Citation Format

Share Document