scholarly journals Face Recognition Framework based on Convolution Neural Network with modified Long Short Term memory Method

2020 ◽  
Vol 1 (3) ◽  
pp. 22-28
Author(s):  
Sushmitha Parikibanda ◽  
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Video Compression ◽  
Short Term Memory ◽  
Detection Algorithm ◽  
Convolution Neural Network ◽  
Learning Approaches ◽  
Short Term ◽  
Commercial Applications ◽  
Experimental Findings

For real-world applications, such as video monitoring, interaction between human machines and safety systems, face recognition is very critical. Deep learning approaches have demonstrated better results in terms of precision and processing speed in image recognition compared to conventional methods. In comparison to traditional methods. While facial detection problems with different commercial applications have been extensively studied for several decades, they still face problems with many specific scenarios, due to various problems such as severe facial occlusions, very low resolutions, intense lighting and exceptional changes in image or video compression artifacts, etc. The aim of this work is to robustly solve the issues listed above with a facial detection approach called Convolution Neural Network with Long short-term Model (CNN-mLSTM). This method first flattened the original frame, calculating the gradient image with Gaussian filter. The edge detection algorithm Canny-Kirsch Method will then be used to identify edge of the human face. The experimental findings suggest that the technique proposed exceeds the current modern methods of face detection.

scholarly journals Quantification of Mental Workload Using a Cascaded Deep One-dimensional Convolution Neural Network and Bi-directional Long Short-Term Memory Model

2021 ◽  
Author(s):  
Vipul Sharma ◽  
Mitul Kumar Ahirwal
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Short Term Memory ◽  
Mental Workload ◽  
Binary Classification ◽  
Convolution Neural Network ◽  
Short Term ◽  
Term Memory ◽  
One Dimensional ◽  
Long Short Term Memory

In this paper, a new cascade one-dimensional convolution neural network (1DCNN) and bidirectional long short-term memory (BLSTM) model has been developed for binary and ternary classification of mental workload (MWL). MWL assessment is important to increase the safety and efficiency in Brain-Computer Interface (BCI) systems and professions where multi-tasking is required. Keeping in mind the necessity of MWL assessment, a two-fold study is presented, firstly binary classification is done to classify MWL into Low and High classes. Secondly, ternary classification is applied to classify MWL into Low, Moderate, and High classes. The cascaded 1DCNN-BLSTM deep learning architecture has been developed and tested over the Simultaneous task EEG workload (STEW) dataset. Unlike recent research in MWL, handcrafted feature extraction and engineering are not done, rather end-to-end deep learning is used over 14 channel EEG signals for classification. Accuracies exceeding the previous state-of-the-art studies have been obtained. In binary and ternary classification accuracies of 96.77% and 95.36% have been achieved with 7-fold cross validation, respectively.

scholarly journals Quantification of Mental Workload Using a Cascaded Deep One-dimensional Convolution Neural Network and Bi-directional Long Short-Term Memory Model

2021 ◽  
Author(s):  
Vipul Sharma ◽  
Mitul Kumar Ahirwal
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Short Term Memory ◽  
Mental Workload ◽  
Binary Classification ◽  
Convolution Neural Network ◽  
Short Term ◽  
Term Memory ◽  
One Dimensional ◽  
Long Short Term Memory

In this paper, a new cascade one-dimensional convolution neural network (1DCNN) and bidirectional long short-term memory (BLSTM) model has been developed for binary and ternary classification of mental workload (MWL). MWL assessment is important to increase the safety and efficiency in Brain-Computer Interface (BCI) systems and professions where multi-tasking is required. Keeping in mind the necessity of MWL assessment, a two-fold study is presented, firstly binary classification is done to classify MWL into Low and High classes. Secondly, ternary classification is applied to classify MWL into Low, Moderate, and High classes. The cascaded 1DCNN-BLSTM deep learning architecture has been developed and tested over the Simultaneous task EEG workload (STEW) dataset. Unlike recent research in MWL, handcrafted feature extraction and engineering are not done, rather end-to-end deep learning is used over 14 channel EEG signals for classification. Accuracies exceeding the previous state-of-the-art studies have been obtained. In binary and ternary classification accuracies of 96.77% and 95.36% have been achieved with 7-fold cross validation, respectively.

scholarly journals A Neural Network in Convolution with Constant Error Carousel Based Long Short Term Memory for Better Face Recognition

2021 ◽  
Vol 12 (2) ◽  
pp. 2042-2052
Author(s):  
P. Ramaraj
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Face Detection ◽  
Short Term Memory ◽  
Constant Error ◽  
Pose Prediction ◽  
Feature Maps ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Unconstrained face identification, facial periocular recognition, facial land marking and pose prediction, facial expression recognition, 3D facial model design, and other facial-related problems require robust face detection in the wild. Despite the fact that the face recognition issue has been researched intensively for decades with different commercial implementations, it nevertheless faces problems in certain real-world scenarios due to multiple obstacles, such as severe facial occlusions, incredibly low resolutions, intense lighting, exceptionally pose inconsistencies, picture or video compression artefacts, and so on. To solve the problems described above, a face detection technique called Convolution Neural Network with Constant Error Carousel dependent Long Short Term Memory (CNN-CEC-LSTM) is proposed in this paper. This research implemented a novel network structure and designed a special feature extraction that employs a self-channel attention (SCA) block and a self-spatial attention (SSA) block that adaptively aggregates the feature maps in both channel and spatial domains to learn the inter-channel and inter-spatial connection matrices; additionally, matrix multiplications are conducted for a This approach first smoothed the initial image with a Gaussian filter before measuring the gradient image. The Canny-Kirsch Method edge detection algorithm was then used to identify human face edges. The proposed method is evaluated against two recent difficult face detection databases, including the IIT Kanpur Dataset. The experimental findings indicate that the proposed approach outperforms the most current cutting-edge face recognition approaches.

Automatic Lip Reading Using Convolution Neural Network and Bidirectional Long Short-term Memory

2019 ◽  
Vol 34 (01) ◽  
pp. 2054003 ◽  
Author(s):  
Yuanyao Lu ◽  
Jie Yan
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Short Term Memory ◽  
Active Contour Model ◽  
Video Clip ◽  
Convolution Neural Network ◽  
Short Term ◽  
Term Memory ◽  
Lip Reading ◽  
Long Short Term Memory

Traditional automatic lip-reading systems generally consist of two stages: feature extraction and recognition, while the handcrafted features are empirical and cannot learn the relevance of lip movement sequence sufficiently. Recently, deep learning approaches have attracted increasing attention, especially the significant improvements of convolution neural network (CNN) applied to image classification and long short-term memory (LSTM) used in speech recognition, video processing and text analysis. In this paper, we propose a hybrid neural network architecture, which integrates CNN and bidirectional LSTM (BiLSTM) for lip reading. First, we extract key frames from each isolated video clip and use five key points to locate mouth region. Then, features are extracted from raw mouth images using an eight-layer CNN. The extracted features have the characteristics of stronger robustness and fault-tolerant capability. Finally, we use BiLSTM to capture the correlation of sequential information among frame features in two directions and the softmax function to predict final recognition result. The proposed method is capable of extracting local features through convolution operations and finding hidden correlation in temporal information from lip image sequences. The evaluation results of lip-reading recognition experiments demonstrate that our proposed method outperforms conventional approaches such as active contour model (ACM) and hidden Markov model (HMM).

Sleep staging by bidirectional long short-term memory convolution neural network

2020 ◽  
Vol 109 ◽  
pp. 188-196 ◽  
Author(s):  
Xueyan Chen ◽  
Jie He ◽  
Xiaoqiang Wu ◽  
Wei Yan ◽  
Wei Wei
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Convolution Neural Network ◽  
Sleep Staging ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

scholarly journals Polar Vortex Multi-Day Intensity Prediction Relying on New Deep Learning Model: A Combined Convolution Neural Network with Long Short-Term Memory Based on Gaussian Smoothing Method

Entropy ◽  
2021 ◽  
Vol 23 (10) ◽  
pp. 1314
Author(s):  
Kecheng Peng ◽  
Xiaoqun Cao ◽  
Bainian Liu ◽  
Yanan Guo ◽  
Chaohao Xiao ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Short Term Memory ◽  
Polar Vortex ◽  
Convolution Neural Network ◽  
Short Term ◽  
Gaussian Smoothing ◽  
Term Memory ◽  
Intensity Prediction ◽  
Long Short Term Memory

The variation of polar vortex intensity is a significant factor affecting the atmospheric conditions and weather in the Northern Hemisphere (NH) and even the world. However, previous studies on the prediction of polar vortex intensity are insufficient. This paper establishes a deep learning (DL) model for multi-day and long-time intensity prediction of the polar vortex. Focusing on the winter period with the strongest polar vortex intensity, geopotential height (GPH) data of NCEP from 1948 to 2020 at 50 hPa are used to construct the dataset of polar vortex anomaly distribution images and polar vortex intensity time series. Then, we propose a new convolution neural network with long short-term memory based on Gaussian smoothing (GSCNN-LSTM) model which can not only accurately predict the variation characteristics of polar vortex intensity from day to day, but also can produce a skillful forecast for lead times of up to 20 days. Moreover, the innovative GSCNN-LSTM model has better stability and skillful correlation prediction than the traditional and some advanced spatiotemporal sequence prediction models. The accuracy of the model suggests important implications that DL methods have good applicability in forecasting the nonlinear system and vortex spatial–temporal characteristics variation in the atmosphere.

Sign in / Sign up

Export Citation Format

Share Document