Signal Processing Methods For Detection Research Articles

PO-04-209 A NOVEL MACHINE LEARNING (ML) ALGORITHM TO MEASURE THE CORRECTED QT INTERVAL FROM MOBILE ECGS WITH HIGH ACCURACY AND PRECISION

The heart rate-corrected QT interval (QTc) is an important feature of the electrocardiogram (ECG), as it is an important prognosticator for ventricular arrhythmia and sudden cardiac death. The 12-lead (12L) ECG is used most often for assessment of QTc, and algorithms that have extended QTc detection to mobile ECGs with fewer than 12 leads are prone to wide sample size deviation. For clinical applications requiring serial QTc monitoring, such as titration of QTc-prolonging drugs, both accuracy and precision are critical. The aim was to develop a novel machine-learning (ML) algorithm that measures QTc from mobile ECG data formats with high accuracy as well as precision. The acceptance criteria was defined as error and standard deviation within 20 milliseconds (ms), the human interobserver variability observed for manual ECG measurements (gold standard). The ML algorithm was trained using a database of 13,000 cardiologist-annotated 12L ECG heartbeats, including the following steps: 1) pre-processing including resampling to 300 Hz, 2) normalization of amplitudes using min-max scaling 3) noisy beats with excessive baseline wander were discarded, and 4) applying TabNet and XGBoost models for detection of the end of T-Wave. This ML model for detection of the T-wave endpoint was merged with a signal processing method for detection of the Q-point. The algorithm was then validated on a subset of 1,239 cardiologist-annotated heartbeats, sufficient to assess strong agreement between software and manual methods (95% CI ± 0.2 std, Bland-Altman approach). Results showed high AUC, sensitivity, and specificity for detecting QTc above clinically meaningful thresholds. Mean QTc error was 5.24±7.22 ms, meeting predefined acceptance criteria. The ML algorithm was then applied to a dataset of 150 6L mECGs (AliveCor; Mountain View, CA), which comprise an all-comer population of a combination of healthy (∼40%), outpatient clinic (30%), and hospitalized patients (30%), with error 13.7±7.78 ms, again meeting acceptance criteria. Algorithm validation surpassed the defined acceptance criteria and demonstrated that the algorithm can provide and potentially surpass human QTc measurement capabilities. By enabling automated, dynamic QTc analysis, the algorithm offered the precision required for outpatient use.

Application of Vibration Signal Processing Methods to Detect and Diagnose Wheel Flats in Railway Vehicles

This paper studied two useful vibration signal processing methods for detection and diagnosis of wheel flats. First, the cepstrum analysis method combined with order analysis was applied to the vibration signal to detect periodic responses in the spectrum for a rotating body such as a wheel. In the case of railway vehicles, changes in speed occur while driving. Thus, it is difficult to effectively evaluate the flat signal of the wheel because the time cycle of the flat signal changes frequently. Thus, the order analysis was combined with the existing cepstrum analysis method to consider the changes in train speed. The order analysis changes the domain of the vibration signal from time domain to rotating angular domain to consider the train speed change in the cepstrum analysis. Second, the cross correlation analysis method combined with the order analysis was applied to evaluate the flat signal from the vibration signal well containing the severe field noise produced by the vibrations of the rail irregularities and bogie components. Unlike the cepstrum analysis method, it can find out the wheel flat size because the flat signal linearly increases to the wheel flat. Thus, it is more effective when checking the size of the wheel flat. Finally, the data tested in the Korea Railroad Research Institute were used to confirm that the cepstrum analysis and cross correlation analysis methods are appropriate for not only simulation but also test data.

Electrodeposition of a magnetic and redox-active chitosan film for capturing and sensing metabolic active bacteria

Rapid and portable detection of viable pathogen is highly desired to minimize the risk of foodborne pathogen outbreaks. Here we report a proof-of-concept fabrication methodology of a multifunctional film that allows established methods from bacterial recognition (antibodies) and nanotechnology (magnetic nanoparticles) to be coupled with electrochemical signal processing methods for detection of viable bacteria. Specifically, we enlist a sequence of externally applied electrical and magnetic signals to: i) guide the self-assembly of stimuli-responsive biopolymer; ii) incorporate magnetic nanoparticles to form a magnetic layer; iii) electro-synthesize a signal processing layer (redox-capacitor). The function of the magnetic layer is collecting and concentrating MMP-bacteria through magnetic attractions between MMP-bacteria and the magnetic layer. The function of the signal processing layer is amplifying electrochemical detection of the collected bacteria by engaging the redox-active mediators with the redox capacitor. Importantly, the fabrication demonstrated here is simple, controllable, and reagentless.

Air-Coupled Ultrasonic Signal Processing Method for Detection of Lamination Defects in Molded Composites

In order to improve signal-to-noise ratio (SNR) of air-coupled ultrasonic signal in the detection of lamination defects in molded composite, the pulse compression and wavelet filtering hybrid signal processing method is proposed. The selection principle of parameters of the hybrid signal processing method is studied. The actual detection results of molded composite show that the hybrid method is very effective in improving the SNR of air-coupled ultrasonic signal when selecting reasonable parameters (The experiment results demonstrate that the optimal parameters are 13-bit Barker code sequences signal with three-cycle per sub-pulse, db9 wavelet, six decomposition levels, and soft threshold function.). An improvement in SNR up to 18.81 dB is attained compared with the original received signal. The quantitative accuracy of defects in C-scan image based on the hybrid method is also very high, and defects as small as $$\emptyset $$ 5 mm can be easily identified.

An Approach for Real-time Levee Health Monitoring Using Signal Processing Methods

We developed a levee health monitoring system within the UrbanFlood project funded under the EU 7th Framework Programme. A novel real-time levee health assessment Artificial Intelligence system is developed using data-driven methods. The system is implemented in the UrbanFlood early warning system. We present the application of dedicated signal processing methods for detection of leakage through the water retaining dam and subsequent analysis of the measurements collected from one of the UrbanFlood pilot levees at the Rhine river in Germany.

Ultrasonic signal processing methods for detection of defects in concrete pipes

Automated inspection systems are important for maintenance and rehabilitation of pipeline systems in North America given their budgetary constraints, demand on providing quality service, and the need for preserving their pipeline infrastructure. Automated ultrasonic signal classification systems are finding increasing use in many applications for the recognition of large volumes of inspection signals. This paper presents an automated signal classification system to process A-scan signals acquired with the Ultrasound transducer from a pipe region of interest (ROI). The overall approach consists of three major steps, preprocessing of the signal, multi-resolution analysis for feature extraction, and neural network classification. Finally, a post processing scheme to interpret the classifier outputs and classify the ROI into an appropriate defect class taking into consideration some a priori knowledge of the problem is developed. The proposed post processing scheme is composed of several steps that combine the statistics from the classification matrix as well as a two-step procedure based on k -nearest neighbor and non-linear regression. The feature extraction, classification and post processing schemes proposed in this paper provide a working proof-of-concept for developing this inspection system into an automated field applicable tool. ► Ultrasonic signal processing. ► Neural network classification methodology. ► Proof-of-concept for automated pipe inspection.

A signal processing method for detecting extremely small diameter thread

A signal processing method for the precise detection of an extremely small diameter thread in a fluctuating environment is proposed in which an analogue signal process is applied to a transient phenomenon. Digital signal processing is applied to a fluctuation rejection algorithm to compensate for vulnerability to noise. Relative signal variations equivalent to 40 μs diameter thread is detected. The signals are processed within 400 μs. Unprecedented noise is rejected by the fluctuation rejection algorithm.