Valley Detection Algorithm Research Articles

SpO2 Measurement: Non-Idealities and Ways to Improve Estimation Accuracy in Wearable Pulse Oximeters

The blood oxygen saturation level (SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) has become one of the vital body parameters for the early detection, monitoring, and tracking of the symptoms of coronavirus diseases 2019 (COVID-19) and is clinically accepted for patient care and diagnostics. Pulse oximetry provides non-invasive SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> monitoring at home and ICUs without the need of a physician/doctor. However, the accuracy of SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> estimation in wearable pulse oximeters remains a challenge due to various non-idealities. We propose a method to improve the estimation accuracy by denoising the red and IR signals, detecting the signal quality, and providing feedback to hardware to adjust the signal chain parameters like LED current or transimpedance amplifier gain and enhance the signal quality. SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> is calculated using the red and infrared photoplethysmogram (PPG) signals acquired from the wrist using Texas Instruments AFE4950EVM. We introduce the green PPG signal as a reference to obtain the window size of the moving average filter for baseline wander removal and as a timing reference for peak and valley detection in the red and infrared PPG signals. We propose the improved peak and valley detection algorithm based on the incremental merge segmentation algorithm. Kurtosis, entropy, and Signal-to-noise ratio (SNR) are used as signal quality parameters, and SNR is further related to the variance in the SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> measurement. A closed-loop implementation is performed to enhance signal quality based on the signal quality parameters of the recorded PPG signals. The proposed algorithm aims to estimate SpO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> with a variance of 1% for the pulse oximetry devices.

SmartJump: A Continuous Jump Detection Framework on Smartphones

Performing jump exercise can maintain a healthy lymphatic system, which keeps human body in an optimal condition and is a critical component of human immune system. Accurate jump detection and count are crucial to patients with a dysfunctional lymph system. In this article, we present a continuous jump detection framework on smartphones, SmartJump, for human jump detection and count, by leveraging the accelerometer and magnetometer ubiquitously built into smartphones. Specifically, SmartJump collects sensing data from the accelerometer and magnetometer, and processes these data through coordinate system translation and data smoothing filter. Then, jump features are extracted based on the smoothed z-axis acceleration data using the peak and valley detection algorithm and then are matched with the concluded three features from the analysis of physical jumps using a finite state machine for jump detection and count. We implement SmartJump on Samsung S6 Edge smartphones and recruit six subjects for data collection. We evaluate the accuracy of SmartJump in terms of five-fold cross-validation test, self-test, and leave-one-out cross-validation test, and the experimental results indicate that SmartJump achieves an average of 96.4 % recall, 97.2 % precision, and 96.8 % F1 score in five different scenarios.

Composite Feature Extraction and Classification for Fusion of Palm-Print and Iris Biometric Traits

Palm-print and iris biometric traits fusion are implemented in this paper. The region of interest (ROI) of a palm is extracted by using the valley detection algorithm and the ROI of an iris is extracted based on the neighbor-pixels value algorithm (NPVA). Statistical local binary pattern (SLBP) is applied to extract the local features of palm and iris. For enhancing the palm features, a combination of histogram of oriented gradient (HOG) and discrete cosine transform (DCT) is applied. Gabor-Zernike moment is used to extract the iris features. This experimentation was carried out in two modes: verification and identification. The Euclidean distance is used in the verification system. In the identification system, the fuzzy-based classifier was proposed along with built-in classification functions in MATLAB. CASIA datasets of palm and iris were used in this research work. The proposed system accuracy was found to be satisfactory.

Extraction of Hand Gesture Features for Indian Sign languages using Combined DWT-DCT and Local Binary Pattern

The Hand Gesture system is based on two modes, viz, Enrollment mode and Recognition mode. In the enrollment mode, the Hand features are acquired from the camera and stored in a database along with the Sign languages. In the recognition mode, the hand features are re-acquired from the camera and compared against the stored Indian sign language data to determine the exact signs. In the pre-processing stage, two segmentation processes are proposed to extract the region of interest (ROI) of hand gesture. The first skin-color segmentation is used to extract the hand image from the background. The second region of interest of the hand gesture is segmented by using the valley detection algorithm. The Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) are applied for the purpose of extracting the features. Further, the Sobel Operator and Local Binary Pattern (LBP) are used for increasing the number of features. The mean and standard deviation of DWT, DCT and LBP are computed.

Classifying Time Series Using Local Descriptors with Hybrid Sampling

Time series classification (TSC) arises in many fields and has a wide range of applications. Here, we adopt the bag-of-words (BoW) framework to classify time series. Our algorithm first samples local subsequences from time series at feature-point locations when available. It then builds local descriptors, and models their distribution by Gaussian mixture models (GMM), and at last it computes a Fisher Vector (FV) to encode each time series. The encoded FV representations of time series are readily used by existing classifiers, e.g., SVM, for training and prediction. In our work, we focus on detecting better feature points and crafting better local representations, while using existing techniques to learn codebook and encode time series. Specifically, we develop an efficient and effective peak and valley detection algorithm from real-case time series data. Subsequences are sampled from these peaks and valleys, instead of sampled randomly or uniformly as was done previously. Then, two local descriptors, Histogram of Oriented Gradients (HOG-1D) and Dynamic time warping-Multidimensional scaling (DTW-MDS), are designed to represent sampled subsequences. Both descriptors complement each other, and their fused representation is shown to be more descriptive than individual ones. We test our approach extensively on 43 UCR time series datasets, and obtain significantly improved classification accuracies over existing approaches, including NNDTW and shapelet transform.

Robust Palmprint Recognition Base on Touch-Less Color Palmprint Images Acquired

In order to make the environment of palmprint recognition more flexible and improve the accuracy of touchless palmprint recognition. This paper proposes a robust, touchless, palmprint recognition system which is based on color palmprint images. This system uses skin-color thresholding and hand valley detection algorithm for extracting palmprint. Then, the local binary pattern (LBP) is applied to the palmprint in order to extract the palmprint features. Finally, chi square statistic is used for classification. The experimental results present the equal error rate of 3.7668% and correct recognition rate of 97.0142%. Therefore the results show that this approach is robust and efficient in color palmprint images which are acquired in lighting changes and cluttered background for touch-less palmprint recognition system.