High-Accuracy Discrimination of Blasts and Earthquakes Using Neural Networks With Multiwindow Spectral Data

Abstract The manual separation of natural earthquakes from mine blasts in data sets recorded by local or regional seismic networks can be a labor-intensive process. An artificial neural network (ANN) applied to automate discriminating earthquakes from quarry and mining blasts in eastern Kentucky suggests that the analyst effort in this task can be significantly reduced. Based on a dataset of 152 local and regional earthquake and 4192 blast recordings over a three-year period in and around eastern Kentucky, ANNs of different configurations were trained and tested on amplitude spectra parameters. The parameters were extracted from different time windows of three-component broadband seismograms to learn the general characteristics of analyst-classified regional earthquake and blast signals. There was little variation in the accuracies and precisions of various models and ANN configurations. The best result used a network with two hidden layers of 256 neurons, trained on an input set of 132 spectral amplitudes and extracted from the P-wave time window and three overlapping time windows from the global maximum amplitude on all three components through the coda. For this configuration and input feature set, 97% of all recordings were accurately classified by our trained model. Furthermore, 96.7% of earthquakes in our data set were correctly classified with mean-event probabilities greater than 0.7. Almost all blasts (98.2%) were correctly classified by mean-event probabilities of at least 0.7. Our technique should greatly reduce the time required for manual inspection of blast recordings. Additionally, our technique circumvents the need for an analyst, or automatic locator, to locate the event ahead of time, a task that is difficult due to the emergent nature of P-wave arrivals induced by delay-fire mine blasts.

Download Full-text

Time Windows Voting Classifier for COVID-19 Mortality Prediction

10.1101/2021.07.02.21259934 ◽

2021 ◽

Author(s):

TIONG GOH ◽

MengJun Liu

Keyword(s):

Time Window ◽

Majority Vote ◽

Time Windows ◽

Mortality Prediction ◽

Data Set ◽

Risk Of Mortality ◽

Machine Learning Model ◽

Partitioned Data ◽

Considerable Impact ◽

Extended Duration

The ability to predict COVID-19 patients' level of severity (death or survival) enables clinicians to prioritise treatment. Recently, using three blood biomarkers, an interpretable machine learning model was developed to predict the mortality of COVID-19 patients. The method was reported to be suffering from performance stability because the identified biomarkers are not consistent predictors over an extended duration. To sustain performance, the proposed method partitioned data into three different time windows. For each window, an end-classifier, a mid-classifier and a front-classifier were designed respectively using the XGboost single tree approach. These time window classifiers were integrated into a majority vote classifier and tested with an isolated test data set. The voting classifier strengthens the overall performance of 90% cumulative accuracy from a 14 days window to a 21 days prediction window. An additional 7 days of prediction window can have a considerable impact on a patient's chance of survival. This study validated the feasibility of the time window voting classifier and further support the selection of biomarkers features set for the early prognosis of patients with a higher risk of mortality.

Download Full-text

Four steps to standardize reporting of peritoneal dialysis technique failure: A proposed approach

Peritoneal Dialysis International ◽

10.1177/0896860820976935 ◽

2020 ◽

pp. 089686082097693

Author(s):

Alix Clarke ◽

Pietro Ravani ◽

Matthew J Oliver ◽

Mohamed Mahsin ◽

Ngan N Lam ◽

...

Keyword(s):

Peritoneal Dialysis ◽

Outcome Measure ◽

Time Window ◽

Time Windows ◽

Dialysis Patients ◽

Data Set ◽

The Impact ◽

Technique Failure ◽

Standardize Reporting ◽

Dialysis Technique

Background: Technique failure is an important outcome measure in research and quality improvement in peritoneal dialysis (PD) programs, but there is a lack of consistency in how it is reported. Methods: We used data collected about incident dialysis patients from 10 Canadian dialysis programs between 1 January 2004 and 31 December 2018. We identified four main steps that are required when calculating the risk of technique failure. We changed one variable at a time, and then all steps, simultaneously, to determine the impact on the observed risk of technique failure at 24 months. Results: A total of 1448 patients received PD. Selecting different cohorts of PD patients changed the observed risk of technique failure at 24 months by 2%. More than one-third of patients who switched to hemodialysis returned to PD—90% returned within 180 days. The use of different time windows of observation for a return to PD resulted in risks of technique failure that differed by 16%. The way in which exit events were handled during the time window impacted the risk of technique failure by 4% and choice of statistical method changed results by 4%. Overall, the observed risk of technique failure at 24 months differed by 20%, simply by applying different approaches to the same data set. Conclusions: The approach to reporting technique failure has an important impact on the observed results. We present a robust and transparent methodology to track technique failure over time and to compare performance between programs.

Download Full-text

Determination of Principal Reynolds Stresses in Pulsatile Flows After Elliptical Filtering of Discrete Velocity Measurements

Journal of Biomechanical Engineering ◽

10.1115/1.2895503 ◽

1993 ◽

Vol 115 (4A) ◽

pp. 396-403 ◽

Cited By ~ 32

Author(s):

J. T. Baldwin ◽

S. Deutsch ◽

H. L. Petrie ◽

J. M. Tarbell

Keyword(s):

Time Window ◽

Laser Doppler Anemometry ◽

Time Windows ◽

Left Ventricular ◽

Data Sets ◽

Reynolds Stresses ◽

Velocity Measurements ◽

Data Set ◽

Data Points ◽

Pulsatile Flows

The purpose of this study was to develop a method to accurately determine mean velocities and Reynolds stresses in pulsatile flows. The pulsatile flow used to develop this method was produced within a transparent model of a left ventricular assist device (LVAD). Velocity measurements were taken at locations within the LVAD using a two-component laser Doppler anemometry (LDA) system. At each measurement location, as many as 4096 realizations of two coincident orthogonal velocity components were collected during preselected time windows over the pump cycle. The number of realizations was varied to determine how the number of data points collected affects the accuracy of the results. The duration of the time windows was varied to determine the maximum window size consistent with an assumption of pseudostationary flow. Erroneous velocity realizations were discarded from individual data sets by implementing successive elliptical filters on the velocity components. The mean velocities and principal Reynolds stresses were determined for each of the filtered data sets. The filtering technique, while eliminating less than 5 percent of the original data points, significantly reduced the computed Reynolds stresses. The results indicate that, with proper filtering, reasonable accuracy can be achieved using a velocity data set of 250 points, provided the time window is small enough to ensure pseudostationary flow (typically 20 to 40 ms). The results also reveal that the time window which is required to assume pseudostationary flow varies with location and cycle time and can range from 100 ms to less than 20 ms. Rotation of the coordinate system to the principal stress axes can lead to large variations in the computed Reynolds stresses, up to 2440 dynes/cm2 for the normal stress and 7620 dynes/cm2 for the shear stress.

Download Full-text

Mastitis Detection from Milk Mid-Infrared (MIR) Spectroscopy in Dairy Cows

Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis ◽

10.11118/actaun201967051221 ◽

2019 ◽

Vol 67 (5) ◽

pp. 1221-1226 ◽

Cited By ~ 3

Author(s):

Lisa Rienesl ◽

Negar Khayatzadeh ◽

Astrid Köck ◽

Laura Dale ◽

Andreas Werner ◽

...

Keyword(s):

Prediction Model ◽

Time Window ◽

Time Windows ◽

Genetic Correlations ◽

Recording System ◽

Data Set ◽

Mid Infrared ◽

Calibration And Validation ◽

Mir Spectroscopy ◽

Mir Spectra

Mid-infrared (MIR) spectroscopy is the method of choice for the standard milk recording system, to determine milk components including fat, protein, lactose and urea. Since milk composition is related to health and metabolic status of a cow, MIR spectra could be potentially used for disease detection. In dairy production, mastitis is one of the most prevalent diseases. The aim of this study was to develop a calibration equation to predict mastitis events from routinely recorded MIR spectra data. A further aim was to evaluate the use of test day somatic cell score (SCS) as covariate on the accuracy of the prediction model. The data for this study is from the Austrian milk recording system and its health monitoring system (GMON). Test day data including MIR spectra data was merged with diagnosis data of Fleckvieh, Brown Swiss and Holstein Friesian cows. As prediction variables, MIR absorbance data after first derivatives and selection of wavenumbers, corrected for days in milk, were used. The data set contained roughly 600,000 records and was split into calibration and validation sets by farm. Calibration sets were made to be balanced (as many healthy as mastitis cases), while the validation set was kept large and realistic. Prediction was done with Partial Least Squares Discriminant Analysis, key indicators of model fit were sensitivity and specificity. Results were extracted for association between spectra and diagnosis with different time windows (days between diagnosis and test days) in validation. The comparison of different sets of predictor variables (MIR, SCS, MIR + SCS) showed an advantage in prediction for MIR + SCS. For this prediction model, specificity was 0.79 and sensitivity was 0.68 in time window -7 to +7 days (calibration and validation). Corresponding values for MIR were 0.71 and 0.61, for SCS they were 0.81 and 0.62. In general, prediction of mastitis performed better with a shorter distance between test day and mastitis event, yet even for time windows of -21 to +21 days, prediction accuracies were still reasonable, with sensitivities ranging from 0.50 to 0.57 and specificities remaining unchanged (0.71 to 0.85). Additional research to further improve prediction equation, and studies on genetic correlations among clinical mastitis, SCS and MIR predicted mastitis are planned.

Download Full-text

A technique for identifying microseismic multiplets and application to the Valhall field, North Sea

Geophysics ◽

10.1190/1.2187804 ◽

2006 ◽

Vol 71 (2) ◽

pp. V31-V40 ◽

Cited By ~ 47

Author(s):

Stephen J. Arrowsmith ◽

Leo Eisner

Keyword(s):

North Sea ◽

Seismic Data ◽

Time Window ◽

Maximum Amplitude ◽

Weighted Average ◽

Correlation Coefficients ◽

Lag Time ◽

S Wave ◽

Data Set ◽

Arithmetic Average

A fast, fully automatic technique to identify microseismic multiplets in borehole seismic data is developed. The technique may be applied in real time to either continuous data or detected-event data for a number of three-component receivers and does not require prior information such as P- or S-wave time picks. Peak crosscorrelation coefficients, evaluated in the frequency domain, are used as the basis for identifying microseismic doublets. The peak crosscorrelation coefficient at each receiver is evaluated with a weighted arithmetic average of the normalized correlation coefficients of each component. Each component is weighted by the maximum amplitude of the signal for that component to reduce the effect of noise on the calculations. The weighted average correlations are averaged over all receivers in a time window centered on a fixed lag time. The size of the time window is determined from the dominant period in the signal, and the lag time is the time that maximizes the average correlation coefficient. The technique is applied to a three-component passive seismic data set recorded at the Valhall field, North Sea. A large number of microseismic doublets are identified that can be grouped into multiplets, reducing the total number of absolute event locations by a factor of two. Seven large multiplets reflect the repeated multiple rerupturing (up to 30 times on a single fault) and significant stress release. Two major faults dominate the seismic activity, causing at least one-fourth of the observed events.

Download Full-text

Reply to comment by Vallée et al. on “Earthquake-induced prompt gravity signals identified in dense array data in Japan”

Earth Planets and Space ◽

10.1186/s40623-019-1099-2 ◽

2019 ◽

Vol 71 (1) ◽

Author(s):

Masaya Kimura ◽

Nobuki Kame ◽

Shingo Watada ◽

Makiko Ohtani ◽

Akito Araya ◽

...

Keyword(s):

Signal Processing ◽

Time Window ◽

Statistical Significance ◽

Low Frequency ◽

Maximum Amplitude ◽

P Wave ◽

Full Account ◽

Frequency Components ◽

Input Acceleration ◽

Broadband Seismograms

AbstractDensity perturbations accompanying seismic waves are expected to generate prompt gravity perturbations preceding the arrival of P-waves. Vallée et al. (Science 358:1164–1168, 2017, https://doi.org/10.1126/science.aao0746) reported the detection of such pre-P-wave signals in broadband seismograms during the 2011 Tohoku-oki earthquake. Kimura et al. (Earth Planets Space 71:27, 2019, https://doi.org/10.1186/s40623-019-1006-x) considered that their detection involved some uncertain points, including a concern regarding their signal processing procedure. Specifically, to remove the instrumental response, Vallée et al. (2017) applied acausal deconvolution to the seismograms truncated at the P-wave arrivals. Generally, acausal deconvolution produces artifacts at the edge of the time window. However, they did not present quantitative assessment whether the detected signals were artifacts due to the signal processing. To avoid this concern, Kimura et al. (2019) employed another procedure that eliminated acausal processes, resulting in the detection of a pre-P-wave signal with a statistical significance of 7σ in stacked broadband seismograms. Subsequently, Vallée et al. (Earth Planets Space 71:51, 2019, https://doi.org/10.1186/s40623-019-1030-x) commented that the procedure employed by Kimura et al. (2019) for the signal detection was inappropriate because it dismissed the low-frequency components of data. Although we admit the loss of low-frequency components in the data in Kimura et al. (2019), Vallée et al. (2019) have not yet provided a full account of the validity of their own procedure. Here, we assessed the validity of the procedure employed by Vallée et al. (2017) by quantitatively evaluating the magnitude of the acausal artifacts. First, we investigated how the input acceleration waveform, having an ideal signal-like shape, was distorted by their procedure. Their acausal deconvolution indeed generated a large-amplitude terminal artifact; however, it was removed by the causal band-pass filtering performed after the deconvolution and consequently became negligible. Next, we constrained the maximum amplitude of the artifact due to the noise in a seismogram and showed that it was sufficiently small compared to the reported signal amplitudes. These results suggest that the signal waveforms seen after their procedure were not artifacts but were representing the input acceleration with sufficient accuracy. Namely, their procedure well functions as a detection method for pre-P-wave signals. In the context of this validation, we replied to the comments of Vallée et al. (2019).

Download Full-text

Amplitude and frequency characteristics of elastic wave types generated by the underground nuclear detonation, Boxcar

Bulletin of the Seismological Society of America ◽

10.1785/bssa0590062283 ◽

1969 ◽

Vol 59 (6) ◽

pp. 2283-2293

Author(s):

W. W. Hays

Keyword(s):

Surface Wave ◽

Elastic Wave ◽

Wave Amplitude ◽

Body Wave ◽

Time Windows ◽

Maximum Amplitude ◽

Propagation Distance ◽

Dominant Frequency ◽

Frequency Characteristics ◽

P Wave

abstract Elastic wave types generated by the Boxcar underground nuclear detonation were identified and analyzed to determine their amplitude and frequency characteristics as a function of distance. The amplitude characteristics of the identified wave types were determined to vary with source to recording station distance and frequency. Within each body wave subset, the refracted wave amplitude decays most rapidly and the reflected wave amplitude least rapidly with distance. Fourier amplitude spectra of the P, S, and surface wave time windows exhibit maxima which occur at different spectral frequencies for stations on rock, ranging from a dominant frequency of about 0.8 Hz for the P-wave window to about 0.25 Hz for the surface wave window. The frequency of the maximum amplitude of each of the three wave mode window spectral sets is essentially unaffected by increase in propagation distance over the distance range 22.2-79.1 km.

Download Full-text

Measurement of the seismoelectric response from a shallow boundary

Geophysics ◽

10.1190/1.1444093 ◽

1996 ◽

Vol 61 (6) ◽

pp. 1769-1778 ◽

Cited By ~ 85

Author(s):

Karl E. Butler ◽

R. Don Russell ◽

Anton W. Kepic ◽

Michael Maxwell

Keyword(s):

Seismic Waves ◽

Field Experiments ◽

Maximum Amplitude ◽

Primary Response ◽

Glacial Till ◽

P Wave ◽

Electrostatic Model ◽

Arrival Times ◽

Time Required ◽

A Site

Field experiments carried out at a site near Vancouver, Canada have shown that a shallow lithologic boundary can be mapped on the basis of its seismoelectric response.As seismic waves cross the boundary between organic‐rich fill and impermeable glacial till, they induceelectric fields that can be measured at the surfacewith grounded dipole receivers. Sledgehammer and blasting cap seismic sources, positioned up to 7 m away from the interface, have produced clear seismoelectric conversions. Two types of seismoelectric signals are observed. The primary response is distinguished by near simultaneous arrivals at widely separated receivers. Its arrival time is equal to the time required for a seismic P‐wave to travel from the shotpoint to the fill/till boundary. On the surface, its maximum amplitude (about 1 mV/m) ismeasured by dipoles located within a few meters of the shotpoint. At greater distances, the amplitude of the primaryarrival decays rapidly with offset, and secondary seismoelectric arrivals become dominant. They differ from the primary response in that their arrival times increasewith dipole offset, and they appear to be generatedin the immediate vicinity of each dipole sensor. Our studies show that the responses cannot be attributedto piezoelectricity or to resistivity modulation in the presence of a uniform telluric current. We infer that seismically induced electrokinetic effects or streamingpotentials are responsible for the seismoelectric conversion,and a simple electrostatic model is proposed to account for the two types of arrivals. Although our experimentswere small in scale, the results are significant in that they suggest that the seismoelectric method may be used to map the boundaries of permeable formations.

Download Full-text

A hybrid ant colony algorithm based on multiple strategies for the vehicle routing problem with time windows

Complex & Intelligent Systems ◽

10.1007/s40747-021-00401-1 ◽

2021 ◽

Author(s):

Hongguang Wu ◽

Yuelin Gao ◽

Wanting Wang ◽

Ziyu Zhang

Keyword(s):

Vehicle Routing ◽

Vehicle Routing Problem ◽

Ant Colony Algorithm ◽

Time Window ◽

Time Windows ◽

Ant Colony ◽

Routing Problem ◽

Multiple Strategies ◽

Hard Time ◽

Mutation Operation

AbstractIn this paper, we propose a vehicle routing problem with time windows (TWVRP). In this problem, we consider a hard time constraint that the fleet can only serve customers within a specific time window. To solve this problem, a hybrid ant colony (HACO) algorithm is proposed based on ant colony algorithm and mutation operation. The HACO algorithm proposed has three innovations: the first is to update pheromones with a new method; the second is the introduction of adaptive parameters; and the third is to add the mutation operation. A famous Solomon instance is used to evaluate the performance of the proposed algorithm. Experimental results show that HACO algorithm is effective against solving the problem of vehicle routing with time windows. Besides, the proposed algorithm also has practical implications for vehicle routing problem and the results show that it is applicable and effective in practical problems.

Download Full-text

The last-mile vehicle routing problem with delivery options

OR Spectrum ◽

10.1007/s00291-021-00633-0 ◽

2021 ◽

Author(s):

Christian Tilk ◽

Katharina Olkis ◽

Stefan Irnich

Keyword(s):

Vehicle Routing ◽

Vehicle Routing Problem ◽

Resource Constraints ◽

Time Window ◽

Time Windows ◽

Service Level ◽

Optimal Solutions ◽

Routing Problem ◽

Common Location ◽

Delivery Options

AbstractThe ongoing rise in e-commerce comes along with an increasing number of first-time delivery failures due to the absence of the customer at the delivery location. Failed deliveries result in rework which in turn has a large impact on the carriers’ delivery cost. In the classical vehicle routing problem (VRP) with time windows, each customer request has only one location and one time window describing where and when shipments need to be delivered. In contrast, we introduce and analyze the vehicle routing problem with delivery options (VRPDO), in which some requests can be shipped to alternative locations with possibly different time windows. Furthermore, customers may prefer some delivery options. The carrier must then select, for each request, one delivery option such that the carriers’ overall cost is minimized and a given service level regarding customer preferences is achieved. Moreover, when delivery options share a common location, e.g., a locker, capacities must be respected when assigning shipments. To solve the VRPDO exactly, we present a new branch-price-and-cut algorithm. The associated pricing subproblem is a shortest-path problem with resource constraints that we solve with a bidirectional labeling algorithm on an auxiliary network. We focus on the comparison of two alternative modeling approaches for the auxiliary network and present optimal solutions for instances with up to 100 delivery options. Moreover, we provide 17 new optimal solutions for the benchmark set for the VRP with roaming delivery locations.

Download Full-text