Signal Quality Assessment of PPG Signals using STFT Time-Frequency Spectra and Deep Learning Approaches

The performance of face analysis and recognition systems depends on the quality of the acquired face data, which is influenced by numerous factors. Automatically assessing the quality of face data in terms of biometric utility can thus be useful to detect low-quality data and make decisions accordingly. This survey provides an overview of the face image quality assessment literature, which predominantly focuses on visible wavelength face image input. A trend towards deep learning based methods is observed, including notable conceptual differences among the recent approaches, such as the integration of quality assessment into face recognition models. Besides image selection, face image quality assessment can also be used in a variety of other application scenarios, which are discussed herein. Open issues and challenges are pointed out, i.a. highlighting the importance of comparability for algorithm evaluations, and the challenge for future work to create deep learning approaches that are interpretable in addition to providing accurate utility predictions.

Download Full-text

application based comparison of statistical versus deep learning approaches to reciprocating compressor valve condition monitoring

Annual Conference of the PHM Society ◽

10.36001/phmconf.2021.v13i1.3081 ◽

2021 ◽

Vol 13 (1) ◽

Author(s):

Jason Kolodziej ◽

Jacob Chesnes

Keyword(s):

Deep Learning ◽

Condition Monitoring ◽

Frequency Analysis ◽

Reciprocating Compressor ◽

Learning Approaches ◽

Early Assessment ◽

Valve Seat ◽

Repeated Impact ◽

Time Frequency Analysis ◽

Time Frequency

This paper presents a vibration-based condition monitoring approach for early assessment of valve wear in an industrial reciprocating compressor. Valve seat wear is a common fault mode that is caused by repeated impact and accelerated by chatter. Seeded faults consistent with valve seat wear are installed on the head-side discharge valves of a Dresser-Rand ESH-1 industrial reciprocating compressor. Due to the cyclostationary nature of these units a time-frequency analysis is employed where targeted crank angle positions can isolate externally mounted, non-invasive, vibration measurements. A region-of-interest (ROI) is then extracted from the time-frequency analysis and used to train a suitably sized convolutional neural network (CNN). The proposed deep learning method is then compared against a similarly trained discriminant classifier using the same ROIs where features are extracted using texture and shape image statistics. Both methods achieve > 90% success with the CNN classification strategy nearing a perfect result.

Download Full-text

Spectral-Based SPD Matrix Representation for Signal Detection Using a Deep Neutral Network

Entropy ◽

10.3390/e22050585 ◽

2020 ◽

Vol 22 (5) ◽

pp. 585 ◽

Cited By ~ 3

Author(s):

Jiangyi Wang ◽

Xiaoqiang Hua ◽

Xinwu Zeng

Keyword(s):

Deep Learning ◽

Signal Detection ◽

Detection Method ◽

Binary Classification ◽

Underlying Structure ◽

Classification Problems ◽

Frequency Spectra ◽

Time Frequency ◽

Target Signal ◽

Simulated Signal

The symmetric positive definite (SPD) matrix has attracted much attention in classification problems because of its remarkable performance, which is due to the underlying structure of the Riemannian manifold with non-negative curvature as well as the use of non-linear geometric metrics, which have a stronger ability to distinguish SPD matrices and reduce information loss compared to the Euclidean metric. In this paper, we propose a spectral-based SPD matrix signal detection method with deep learning that uses time-frequency spectra to construct SPD matrices and then exploits a deep SPD matrix learning network to detect the target signal. Using this approach, the signal detection problem is transformed into a binary classification problem on a manifold to judge whether the input sample has target signal or not. Two matrix models are applied, namely, an SPD matrix based on spectral covariance and an SPD matrix based on spectral transformation. A simulated-signal dataset and a semi-physical simulated-signal dataset are used to demonstrate that the spectral-based SPD matrix signal detection method with deep learning has a gain of 1.7–3.3 dB under appropriate conditions. The results show that our proposed method achieves better detection performances than its state-of-the-art spectral counterparts that use convolutional neural networks.

Download Full-text

Speaker Identification using Machine Learning

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.l3179.119119 ◽

2019 ◽

Vol 9 (1) ◽

pp. 1216-1218

Keyword(s):

Deep Learning ◽

Speaker Identification ◽

Frequency Assignment ◽

Learning Approaches ◽

Speech Separation ◽

Rest Point ◽

Time Frequency ◽

Learning Framework ◽

Frequency Representation ◽

Permutation Problem

Whatever the modern achievement of deep learning for several terminology processing tasks, single-microphone, speaker-independent speech separation remains difficult for just two main things. The rest point is that the arbitrary arrangement of the goal and masker speakers in the combination (permutation problem), and also the following is the unidentified amount of speakers in the mix (output issue). We suggest a publication profound learning framework for speech modification, which handles both issues. We work with a neural network to project the specific time-frequency representation with the mixed-signal to a high-dimensional categorizing region. The time-frequency embeddings of the speaker have then made to an audience around corresponding attractor stage that is employed to figure out the time-frequency assignment with this speaker identifying a speaker using a blend of speakers together with the aid of neural networks employing deep learning. The purpose function for your machine is standard sign renovation error that allows finishing functioning throughout both evaluation and training periods. We assessed our system with all the voices of users three and two speaker mixes and also document similar or greater performance when compared with another advanced level, deep learning approaches for speech separation.

Download Full-text

Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks

Sensors ◽

10.3390/s19143079 ◽

2019 ◽

Vol 19 (14) ◽

pp. 3079 ◽

Cited By ~ 16

Author(s):

Attila Reiss ◽

Ina Indlekofer ◽

Philip Schmidt ◽

Kristof Van Laerhoven

Keyword(s):

Heart Rate ◽

Deep Learning ◽

Large Scale ◽

Learning Approach ◽

Frequency Spectra ◽

Time Frequency ◽

Rate Estimation ◽

Wide Range ◽

Public Datasets ◽

Heart Rate Estimation

Photoplethysmography (PPG)-based continuous heart rate monitoring is essential in a number of domains, e.g., for healthcare or fitness applications. Recently, methods based on time-frequency spectra emerged to address the challenges of motion artefact compensation. However, existing approaches are highly parametrised and optimised for specific scenarios of small, public datasets. We address this fragmentation by contributing research into the robustness and generalisation capabilities of PPG-based heart rate estimation approaches. First, we introduce a novel large-scale dataset (called PPG-DaLiA), including a wide range of activities performed under close to real-life conditions. Second, we extend a state-of-the-art algorithm, significantly improving its performance on several datasets. Third, we introduce deep learning to this domain, and investigate various convolutional neural network architectures. Our end-to-end learning approach takes the time-frequency spectra of synchronised PPG- and accelerometer-signals as input, and provides the estimated heart rate as output. Finally, we compare the novel deep learning approach to classical methods, performing evaluation on four public datasets. We show that on large datasets the deep learning model significantly outperforms other methods: The mean absolute error could be reduced by 31 % on the new dataset PPG-DaLiA, and by 21 % on the dataset WESAD.

Download Full-text

Heart Sound Signal Quality Assessment Based on Multi-Domain Features

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2020.2926 ◽

2020 ◽

Vol 10 (3) ◽

pp. 736-742

Author(s):

Yu Jiao ◽

Xinpei Wang ◽

Changchun Liu ◽

Han Li ◽

Huan Zhang ◽

...

Keyword(s):

Feature Selection ◽

Statistical Analysis ◽

Quality Assessment ◽

Heart Sound ◽

Feature Selection Method ◽

Sound Signal ◽

Signal Quality ◽

Deep Breath ◽

Time Frequency ◽

Heart Sound Signal

Heart sound is one of the most important physiological signals of our body, including a large number of physiological and pathological information that can reflect the cardiovascular status. This study aims to develop a heart sound signal quality assessment method. In view of the 3 common noises (deep breath, speaking and cough) in clinical data collection, a total of 72 features were extracted from 6 domains, i.e., time, frequency, entropy, energy, high-order statistics and cyclostationarity. Then information gain, which was used as feature selection method, as well as statistical analysis were employed for dimension reduction. A SVM with radial basis kernel function was trained for final signal quality classification. The best effect was obtained on distinguishing resting from cough and the result showed that the classification performance was significantly improved after feature selection. In contrast, statistical analysis had little effect on the improvement of classification results. The best accuracy in distinguishing between resting and deep breath, resting and speaking, resting and cough is 87.73%, 95.00%, 98.64%, respectively. These results indicate that the proposed method is effective for identifying different noise states, namely cough, speaking and deep breath.

Download Full-text

Deep Learning Approaches for Whiteboard Image Quality Enhancement

Color and Imaging Conference ◽

10.2352/j.imagingsci.technol.2019.63.4.040404 ◽

2019 ◽

Vol 2019 (1) ◽

pp. 360-368

Author(s):

Mekides Assefa Abebe ◽

Jon Yngve Hardeberg

Keyword(s):

Deep Learning ◽

Image Quality ◽

Image Data ◽

Quality Enhancement ◽

Network Architectures ◽

Learning Approaches ◽

Data Set ◽

Image Quality Enhancement ◽

Processing Techniques ◽

White Balancing

Different whiteboard image degradations highly reduce the legibility of pen-stroke content as well as the overall quality of the images. Consequently, different researchers addressed the problem through different image enhancement techniques. Most of the state-of-the-art approaches applied common image processing techniques such as background foreground segmentation, text extraction, contrast and color enhancements and white balancing. However, such types of conventional enhancement methods are incapable of recovering severely degraded pen-stroke contents and produce artifacts in the presence of complex pen-stroke illustrations. In order to surmount such problems, the authors have proposed a deep learning based solution. They have contributed a new whiteboard image data set and adopted two deep convolutional neural network architectures for whiteboard image quality enhancement applications. Their different evaluations of the trained models demonstrated their superior performances over the conventional methods.

Download Full-text