Using long short term memory and convolutional neural networks for driver drowsiness detection

Abstract. It is now well established to use shallow artificial neural networks (ANNs) to obtain accurate and reliable groundwater level forecasts, which are an important tool for sustainable groundwater management. However, we observe an increasing shift from conventional shallow ANNs to state-of-the-art deep-learning (DL) techniques, but a direct comparison of the performance is often lacking. Although they have already clearly proven their suitability, shallow recurrent networks frequently seem to be excluded from the study design due to the euphoria about new DL techniques and its successes in various disciplines. Therefore, we aim to provide an overview on the predictive ability in terms of groundwater levels of shallow conventional recurrent ANNs, namely non-linear autoregressive networks with exogenous input (NARX) and popular state-of-the-art DL techniques such as long short-term memory (LSTM) and convolutional neural networks (CNNs). We compare the performance on both sequence-to-value (seq2val) and sequence-to-sequence (seq2seq) forecasting on a 4-year period while using only few, widely available and easy to measure meteorological input parameters, which makes our approach widely applicable. Further, we also investigate the data dependency in terms of time series length of the different ANN architectures. For seq2val forecasts, NARX models on average perform best; however, CNNs are much faster and only slightly worse in terms of accuracy. For seq2seq forecasts, mostly NARX outperform both DL models and even almost reach the speed of CNNs. However, NARX are the least robust against initialization effects, which nevertheless can be handled easily using ensemble forecasting. We showed that shallow neural networks, such as NARX, should not be neglected in comparison to DL techniques especially when only small amounts of training data are available, where they can clearly outperform LSTMs and CNNs; however, LSTMs and CNNs might perform substantially better with a larger dataset, where DL really can demonstrate its strengths, which is rarely available in the groundwater domain though.

Download Full-text

A Comparison of Power Quality Disturbance Detection and Classification Methods Using CNN, LSTM and CNN-LSTM

Applied Sciences ◽

10.3390/app10196755 ◽

2020 ◽

Vol 10 (19) ◽

pp. 6755

Author(s):

Carlos Iturrino Garcia ◽

Francesco Grasso ◽

Antonio Luchetta ◽

Maria Cristina Piccirilli ◽

Libero Paolucci ◽

...

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Data Augmentation ◽

Short Term Memory ◽

Machine Learning Algorithms ◽

Validation Dataset ◽

Short Term ◽

Current Time ◽

Term Memory ◽

Long Short Term Memory

The use of electronic loads has improved many aspects of everyday life, permitting more efficient, precise and automated process. As a drawback, the nonlinear behavior of these systems entails the injection of electrical disturbances on the power grid that can cause distortion of voltage and current. In order to adopt countermeasures, it is important to detect and classify these disturbances. To do this, several Machine Learning Algorithms are currently exploited. Among them, for the present work, the Long Short Term Memory (LSTM), the Convolutional Neural Networks (CNN), the Convolutional Neural Networks Long Short Term Memory (CNN-LSTM) and the CNN-LSTM with adjusted hyperparameters are compared. As a preliminary stage of the research, the voltage and current time signals are simulated using MATLAB Simulink. Thanks to the simulation results, it is possible to acquire a current and voltage dataset with which the identification algorithms are trained, validated and tested. These datasets include simulations of several disturbances such as Sag, Swell, Harmonics, Transient, Notch and Interruption. Data Augmentation techniques are used in order to increase the variability of the training and validation dataset in order to obtain a generalized result. After that, the networks are fed with an experimental dataset of voltage and current field measurements containing the disturbances mentioned above. The networks have been compared, resulting in a 79.14% correct classification rate with the LSTM network versus a 84.58% for the CNN, 84.76% for the CNN-LSTM and a 83.66% for the CNN-LSTM with adjusted hyperparameters. All of these networks are tested using real measurements.

Download Full-text

Finger-Vein Verification Based on LSTM Recurrent Neural Networks

Applied Sciences ◽

10.3390/app9081687 ◽

2019 ◽

Vol 9 (8) ◽

pp. 1687 ◽

Cited By ~ 4

Author(s):

Huafeng Qin ◽

Peng Wang

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Short Term Memory ◽

Support Vector ◽

Short Term ◽

Vein Pattern ◽

Term Memory ◽

Finger Vein ◽

Spatial Dependencies ◽

Long Short Term Memory

Finger-vein biometrics has been extensively investigated for personal verification. A challenge is that the finger-vein acquisition is affected by many factors, which results in many ambiguous regions in the finger-vein image. Generally, the separability between vein and background is poor in such regions. Despite recent advances in finger-vein pattern segmentation, current solutions still lack the robustness to extract finger-vein features from raw images because they do not take into account the complex spatial dependencies of vein pattern. This paper proposes a deep learning model to extract vein features by combining the Convolutional Neural Networks (CNN) model and Long Short-Term Memory (LSTM) model. Firstly, we automatically assign the label based on a combination of known state of the art handcrafted finger-vein image segmentation techniques, and generate various sequences for each labeled pixel along different directions. Secondly, several Stacked Convolutional Neural Networks and Long Short-Term Memory (SCNN-LSTM) models are independently trained on the resulting sequences. The outputs of various SCNN-LSTMs form a complementary and over-complete representation and are conjointly put into Probabilistic Support Vector Machine (P-SVM) to predict the probability of each pixel of being foreground (i.e., vein pixel) given several sequences centered on it. Thirdly, we propose a supervised encoding scheme to extract the binary vein texture. A threshold is automatically computed by taking into account the maximal separation between the inter-class distance and the intra-class distance. In our approach, the CNN learns robust features for vein texture pattern representation and LSTM stores the complex spatial dependencies of vein patterns. So, the pixels in any region of a test image can then be classified effectively. In addition, the supervised information is employed to encode the vein patterns, so the resulting encoding images contain more discriminating features. The experimental results on one public finger-vein database show that the proposed approach significantly improves the finger-vein verification accuracy.

Download Full-text