Gait-Based Identification Using Deep Recurrent Neural Networks and Acceleration Patterns

This manuscript presents an approach to the challenge of biometric identification based on the acceleration patterns generated by a user while walking. The proposed approach uses the data captured by a smartphone’s accelerometer and gyroscope sensors while the users perform the gait activity and optimizes the design of a recurrent neural network (RNN) to optimally learn the features that better characterize each individual. The database is composed of 15 users, and the acceleration data provided has a tri-axial format in the X-Y-Z axes. Data are pre-processed to estimate the vertical acceleration (in the direction of the gravity force). A deep recurrent neural network model consisting of LSTM cells divided into several layers and dense output layers is used for user recognition. The precision results obtained by the final architecture are above 97% in most executions. The proposed deep neural network-based architecture is tested in different scenarios to check its efficiency and robustness.

Download Full-text

Failure Prognosis of Complex Equipment With Multistream Deep Recurrent Neural Network

Journal of Computing and Information Science in Engineering ◽

10.1115/1.4045445 ◽

2020 ◽

Vol 20 (2) ◽

Cited By ~ 4

Author(s):

Yonghe Su ◽

Fei Tao ◽

Jian Jin ◽

Tian Wang ◽

Qingguo Wang ◽

...

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Deep Neural Network ◽

Health Management ◽

Large Data ◽

Vibration Signal ◽

Linear Layer ◽

Deep Recurrent Neural Network ◽

Complex Equipment ◽

Failure Prognosis

Abstract The failure prognosis is crucial for industrial equipment in prognostics and health management field. The vibration signal is the commonly used data for failure prognosis. The conventional prognostic approaches have limitations to handle the features extracted from the vibration signal because of the large data quantity, complex feature relations, and limited degeneration mechanisms. In this paper, a deep learning-based approach is proposed to predict the failure of the complex equipment. To supply plenty of features, three different domain features are extracted from vibration signals. Next, these features are preprocessed and reconstructed by arctangent normalization and data stream, respectively. Finally, a deep neural network, namely, multistream deep recurrent neural network (MS-DRNN) is built to fuse these features for failure target. The presented deep neural network is hybrid, involving recurrent layer, fusion layer, fully connected layer, and linear layer. To benchmark the proposed approach, several prognosis approaches are evaluated with the testing data from six large bearing datasets. Simulation results demonstrate that the prediction performance of the MS-DRNN-based approach is effective and reliable.

Download Full-text

ECG Identification For Personal Authentication Using LSTM-Based Deep Recurrent Neural Networks

Sensors ◽

10.3390/s20113069 ◽

2020 ◽

Vol 20 (11) ◽

pp. 3069 ◽

Cited By ~ 2

Author(s):

Beom-Hun Kim ◽

Jae-Young Pyun

Keyword(s):

Neural Network ◽

Neural Networks ◽

Real Time ◽

Recurrent Neural Network ◽

Recurrent Neural Networks ◽

Support Vector ◽

Time System ◽

Real Time System ◽

Deep Recurrent Neural Network ◽

Personal Authentication

Securing personal authentication is an important study in the field of security. Particularly, fingerprinting and face recognition have been used for personal authentication. However, these systems suffer from certain issues, such as fingerprinting forgery, or environmental obstacles. To address forgery or spoofing identification problems, various approaches have been considered, including electrocardiogram (ECG). For ECG identification, linear discriminant analysis (LDA), support vector machine (SVM), principal component analysis (PCA), deep recurrent neural network (DRNN), and recurrent neural network (RNN) have been conventionally used. Certain studies have shown that the RNN model yields the best performance in ECG identification as compared with the other models. However, these methods require a lengthy input signal for high accuracy. Thus, these methods may not be applied to a real-time system. In this study, we propose using bidirectional long short-term memory (LSTM)-based deep recurrent neural networks (DRNN) through late-fusion to develop a real-time system for ECG-based biometrics identification and classification. We suggest a preprocessing procedure for the quick identification and noise reduction, such as a derivative filter, moving average filter, and normalization. We experimentally evaluated the proposed method using two public datasets: MIT-BIH Normal Sinus Rhythm (NSRDB) and MIT-BIH Arrhythmia (MITDB). The proposed LSTM-based DRNN model shows that in NSRDB, the overall precision was 100%, recall was 100%, accuracy was 100%, and F1-score was 1. For MITDB, the overall precision was 99.8%, recall was 99.8%, accuracy was 99.8%, and F1-score was 0.99. Our experiments demonstrate that the proposed model achieves an overall higher classification accuracy and efficiency compared with the conventional LSTM approach.

Download Full-text

Jaya Ant Lion Optimization-Driven Deep Recurrent Neural Network for Cancer Classification Using Gene Expression Data (Preprint)

10.2196/preprints.25962 ◽

2020 ◽

Author(s):

Ramachandro Majji

Keyword(s):

Neural Network ◽

Recurrent Neural Network ◽

Early Stage ◽

Data Transformation ◽

Cancer Classification ◽

Data Normalization ◽

Ant Lion Optimization ◽

Deep Recurrent Neural Network ◽

Novel Strategy ◽

Feature Dimension

BACKGROUND Cancer is one of the deadly diseases prevailing worldwide and the patients with cancer are rescued only when the cancer is detected at the very early stage. Early detection of cancer is essential as, in the final stage, the chance of survival is limited. The symptoms of cancers are rigorous and therefore, all the symptoms should be studied properly before the diagnosis. OBJECTIVE Propose an automatic prediction system for classifying cancer to malignant or benign. METHODS This paper introduces the novel strategy based on the JayaAnt lion optimization-based Deep recurrent neural network (JayaALO-based DeepRNN) for cancer classification. The steps followed in the developed model are data normalization, data transformation, feature dimension detection, and classification. The first step is the data normalization. The goal of data normalization is to eliminate data redundancy and to mitigate the storage of objects in a relational database that maintains the same information in several places. After that, the data transformation is carried out based on log transformation that generates the patterns using more interpretable and helps fulfill the supposition, and to reduce skew. Also, the non-negative matrix factorization is employed for reducing the feature dimension. Finally, the proposed JayaALO-based DeepRNN method effectively classifies cancer-based on the reduced dimension features to produce a satisfactory result. RESULTS The proposed JayaALO-based DeepRNN showed improved results with maximal accuracy of 95.97%, the maximal sensitivity of 95.95%, and the maximal specificity of 96.96%. CONCLUSIONS The resulted output of the proposed JayaALO-based DeepRNN is used for cancer classification.

Download Full-text