Machine learning and feature engineering for predicting pulse presence during chest compressions

In Australia, party sparklers are commonly used to initiate or prepare inorganic based homemade explosives (HMEs) as they are the most easily accessible and inexpensive pyrotechnic available on the market. As sparkler residue would be encountered in cases involving these types of devices, the characterisation and source determination of the residue would be beneficial within a forensic investigation. The aim of this study is to demonstrate the potential of using trace elemental profiling coupled with chemometric and other statistical techniques to link a variety of different sparklers to their origin. Inductively coupled plasma – mass spectrometry (ICP-MS) was used to determine the concentration of 50 elements in 48 pre-blast sparkler samples from eight sparkler brands/classes available in Australia. Extracting ground-up sparkler residue in 10% nitric acid for 24 hours was found to give the most reliable quantification. The collected data were analysed using Principal Component Analysis (PCA) to visualise the distribution of the sample data and explore whether the sparkler samples could be classified into their respective brands. ANOVA based feature selection was used to remove elements that did not significantly contribute to the separation between classes. This resulted in the development of a 7-elemental profile, consisting of V, Co, Ni, Sr, Sn, Sb, W, which could be used to correctly classify the samples into eight distinct groups. Linear Discriminant Analysis (LDA) was subsequently used to construct a discriminant model using four out of six samples from each class. The model successfully classified 100% of the samples to their correct sparkler brand. The model also correctly matched 100% of the remaining samples to the correct class. This demonstrates the potential of using trace elemental analysis and chemometrics to correctly identify and discriminate between party sparklers.

Download Full-text

Study on discrimination of different grades of rapeseed oil based on flavor fingerprint

Acta Chromatographica ◽

10.1556/1326.2020.00817 ◽

2020 ◽

Author(s):

Tong Chen ◽

Chunyou Liu ◽

Bin Chen ◽

Yongchun Huang

Keyword(s):

Rapeseed Oil ◽

Solid Phase ◽

Oil Quality ◽

Recognition Rate ◽

Principal Component ◽

Internal Quality ◽

Extraction Technology ◽

Linear Discriminant ◽

Discriminant Model ◽

The Relationship

AbstractIn this work, Gas chromatograph-Mass Spectrometry (GC-MS) combined with solid phase micro-extraction technology was used to analyze the difference of volatile organic compounds (VOCs) in rapeseed oil of different grades, and the relationship between changes of VOCs and refining process were also investigated in order to construct a non-linear model, which could realize rapid and accurate discrimination of different grade rapeseed oils. 124 rapeseed oil samples with different grades were collected and analyzed by GC-MS technology and 55 VOCs were identified and selected as variables to characterize the internal quality information of rapeseed oils. Then, principal component analysis (PCA) method was used to extract useful features and reduce data dimensionality, and finally a discriminant model was built using linear discriminant analysis (LDA) algorithm. The correct recognition rate of sample set was close to 94.59%. The results showed that the proposed method is promising in discriminating different grades of vegetable oils. Besides, it provides a theoretical basis for studying the relationship between VOCs composition and vegetable oil quality.

Download Full-text

Abstract 1: Statewide Implementation of a Standardized Prearrival Telephone CPR Program Is Associated with Increased Bystander CPR and Survival from Out-of-Hospital Cardiac Arrest

Circulation ◽

10.1161/circ.130.suppl_2.1 ◽

2014 ◽

Vol 130 (suppl_2) ◽

Author(s):

Bentley Bobrow ◽

Micah Panczyk ◽

Uwe Stolz ◽

Mike Sotelo ◽

Tyler Vadeboncoeur ◽

...

Keyword(s):

Data Collection ◽

Outcome Data ◽

Training Data ◽

Audio Recordings ◽

Process And Outcome ◽

Good Neurologic Outcome ◽

Bystander Cpr ◽

Multivariable Analyses ◽

The Impact ◽

Hospital Cardiac Arrest

Background: Bystander CPR (BCPR) increases survival from OHCA yet is provided in a minority of cases. The AHA has promulgated guidelines on the provision of pre-arrival Telephone CPR (TCPR) instructions and measurement to increase the proportion of BCPR; however, the impact of those guidelines on survival is unknown. Objective: To describe the impact of a comprehensive bundle of 9-1-1 TCPR protocol, training, data collection, and feedback on BCPR and survival from OHCA across the state of Arizona. Methods: 9-1-1 audio recordings of confirmed OHCAs and suspected OHCAs (10/2010-6/2013) in 7 large 9-1-1 centers were reviewed using a standardized time-stamp methodology linked with EMS and hospital process and outcome data. There were 2343 pre-implementation cases (P1) and 2291 cases post-implementation of a bundle of care (P2) that included staff training and guideline-based protocol changes, data collection and feedback to providers. Univariate and multivariable analyses were used to assess outcomes between P1 and P2. Results: There were 2532 OHCAs [1232 P1, 1300 P2; 64% male, median age 62 (IQR: 47-74)]. 83% of cases were identified in P1 compared with 89% in P2 (p<0.001). The rate of telephone-assisted BCPR went from 44% in P1 to 62% in P2 (p<0.001). Time to beginning TCPR instructions decreased from a median of 144 sec (P1) to 126 in P2 (p<0.001). Time to first chest compression also decreased (P1: 178; P2: 155; p<0.001). Outcome data are currently available for 64% of confirmed OHCAs (1630 patient outcomes with 1619 neuro outcomes). Survival was significantly higher in P2 (11.2%) compared to P1 (7.9%; p=0.023), as was good neuro outcome (CPC-1 or 2: 7.7% P2 vs. 4.8% P1 p=0.018). After adjusting for witnessed arrest, shockable rhythms, age, and sex, both survival and good neuro outcome were still significantly higher in P2 vs. P1 [adjusted odds ratios: survival = 1.5 (95% 1.1-2.1); good neuro outcome = 1.7 (95% 1.1-2.6)]. Conclusion: The implementation of a comprehensive statewide TCPR bundle was associated with significant improvements in the rates of telephone-assisted BCPR, survival and good neurologic outcome after OHCA.

Download Full-text

Preliminary Investigations into the Source Attribution of Party Sparklers Using Trace Elemental Analysis and Chemometrics

10.26434/chemrxiv.12585365.v2 ◽

2020 ◽

Author(s):

Joshua D'Uva ◽

David DeTata ◽

Christopher D. May ◽

Simon W. Lewis

Keyword(s):

Elemental Analysis ◽

Inductively Coupled Plasma ◽

Principal Component ◽

Source Attribution ◽

Trace Elemental Analysis ◽

Linear Discriminant ◽

Inductively Coupled ◽

Discriminant Model ◽

Source Determination ◽

Trace Elemental

In Australia, party sparklers are commonly used to initiate or prepare inorganic based homemade explosives (HMEs) as they are the most easily accessible and inexpensive pyrotechnic available on the market. As sparkler residue would be encountered in cases involving these types of devices, the characterisation and source determination of the residue would be beneficial within a forensic investigation. The aim of this study is to demonstrate the potential of using trace elemental profiling coupled with chemometric and other statistical techniques to link a variety of different sparklers to their origin. Inductively coupled plasma – mass spectrometry (ICP-MS) was used to determine the concentration of 50 elements in 48 pre-blast sparkler samples from eight sparkler brands/classes available in Australia. Extracting ground-up sparkler residue in 10% nitric acid for 24 hours was found to give the most reliable quantification. The collected data were analysed using Principal Component Analysis (PCA) to visualise the distribution of the sample data and explore whether the sparkler samples could be classified into their respective brands. ANOVA based feature selection was used to remove elements that did not significantly contribute to the separation between classes. This resulted in the development of a 7-elemental profile, consisting of V, Co, Ni, Sr, Sn, Sb, W, which could be used to correctly classify the samples into eight distinct groups. Linear Discriminant Analysis (LDA) was subsequently used to construct a discriminant model using four out of six samples from each class. The model successfully classified 100% of the samples to their correct sparkler brand. The model also correctly matched 100% of the remaining samples to the correct class. This demonstrates the potential of using trace elemental analysis and chemometrics to correctly identify and discriminate between party sparklers.

Download Full-text

An Evaluation of the Channel Effect on Detecting the Preictal Stage in Patients With Epilepsy

Clinical EEG and Neuroscience ◽

10.1177/1550059420966436 ◽

2020 ◽

pp. 155005942096643

Author(s):

Erhan Bergil ◽

Mehmet Recep Bozkurt ◽

Canan Oral

Keyword(s):

Principal Component ◽

Epileptic Seizures ◽

Training Data ◽

Eeg Signals ◽

Linear Discriminant ◽

Testing Data ◽

Patients With Epilepsy ◽

Electrode Selection ◽

And Training ◽

Selection Of

Decreasing the processor load to an acceptable level challenges researchers as an important threshold in the study of real-time detection and the prediction of epileptic seizures. The main methods in overcoming this problem are feature selection, dimension reduction, and electrode selection. This study is an evaluation of the performances of EEG signals, obtained from different channels in the detection processes of epileptic stages, in epileptic individuals. In particular, it aimed to analyze the separation levels of preictal periods from other periods and to evaluate the effects of the electrode selection on seizure prediction studies. The EEG signals belong to 14 epileptic patients. A feature set was formed for each patient using 20 features widely used in epilepsy studies. The number of features was decreased to 8 using principal component analysis. The reduced feature set was divided into testing and training data, using the cross-validation method. The testing data were classified with linear discriminant analysis and the results of the classification were evaluated individually for each patient and channel. Variability of up to 29.48 % was observed in the average of classification accuracy due to the selection of channels.

Download Full-text

Preliminary Investigations into the Source Attribution of Party Sparklers Using Trace Elemental Analysis and Chemometrics

10.26434/chemrxiv.12585365 ◽

2020 ◽

Author(s):

Joshua D'Uva ◽

David DeTata ◽

Christopher D. May ◽

Simon W. Lewis

Keyword(s):

Elemental Analysis ◽

Inductively Coupled Plasma ◽

Principal Component ◽

Source Attribution ◽

Trace Elemental Analysis ◽

Linear Discriminant ◽

Inductively Coupled ◽

Discriminant Model ◽

Source Determination ◽

Trace Elemental

In Australia, party sparklers are commonly used to initiate or prepare inorganic based homemade explosives (HMEs) as they are the most easily accessible and inexpensive pyrotechnic available on the market. As sparkler residue would be encountered in cases involving these types of devices, the characterisation and source determination of the residue would be beneficial within a forensic investigation. The aim of this study is to demonstrate the potential of using trace elemental profiling coupled with chemometric and other statistical techniques to link a variety of different sparklers to their origin. Inductively coupled plasma – mass spectrometry (ICP-MS) was used to determine the concentration of 50 elements in 48 pre-blast sparkler samples from eight sparkler brands/classes available in Australia. Extracting ground-up sparkler residue in 10% nitric acid for 24 hours was found to give the most reliable quantification. The collected data were analysed using Principal Component Analysis (PCA) to visualise the distribution of the sample data and explore whether the sparkler samples could be classified into their respective brands. ANOVA based feature selection was used to remove elements that did not significantly contribute to the separation between classes. This resulted in the development of a 7-elemental profile, consisting of V, Co, Ni, Sr, Sn, Sb, W, which could be used to correctly classify the samples into eight distinct groups. Linear Discriminant Analysis (LDA) was subsequently used to construct a discriminant model using four out of six samples from each class. The model successfully classified 100% of the samples to their correct sparkler brand. The model also correctly matched 100% of the remaining samples to the correct class. This demonstrates the potential of using trace elemental analysis and chemometrics to correctly identify and discriminate between party sparklers.

Download Full-text

Abstract 298: Predicting Pulse Status During Cardiopulmonary Resuscitation Using Dimensionality Reduction of Electrocardiogram Wavelet Transforms

Circulation ◽

10.1161/circ.142.suppl_4.298 ◽

2020 ◽

Vol 142 (Suppl_4) ◽

Author(s):

Diya Sashidhar ◽

Heemun Kwok ◽

Jason Coult ◽

Jennifer E Blackwood ◽

Peter J Kudenchuk ◽

...

Keyword(s):

Cardiopulmonary Resuscitation ◽

Wavelet Transforms ◽

Characteristic Curve ◽

Model Performance ◽

Test Group ◽

Training Data ◽

Linear Discriminant ◽

Principle Component ◽

Pulse Check ◽

Receiver Operating

Background: Current resuscitation protocols require pausing cardiopulmonary resuscitation (CPR) to check for a pulse. However, pausing CPR during a pulseless rhythm worsens patient outcome. We designed an ECG-based algorithm that predicts pulse status during uninterrupted CPR, and evaluated its performance both with and without CPR. Methods: We evaluated 383 patients who were treated for out-of-hospital cardiac arrest using defibrillators with real-time ECG, CPR, and audio recordings. We collected paired adjacent ECG segments with and without CPR during organized rhythms. Segments were collected during the 10-s CPR period just prior to pulse check, and 5-s segments without CPR during the pulse check. ECG segments with or without a pulse were identified by the audio annotation and recorded blood pressures. Patients were randomly divided into 60% (230/383) training and 40% (153/383) test groups. From training data, we developed an algorithm to predict clinical pulse status based on the wavelet transform of the bandpass-filtered ECG, applying principle component analysis (PCA). We then trained a linear discriminant model using 3 principle component modes as input features. Model performance was evaluated on test group segments with and without CPR using receiver operating curves overall and according to initial arrest rhythm. Results: There were 230 patients (540 pulse checks) in the training set and 153 patients (372 pulse checks) in the test set. In both of these sets, about 16% (37/230 and 25/153) of the patients presented with initial non-shockable rhythm . Overall 38% (351/912) of checks had a spontaneous pulse. The areas under the receiver operating characteristic curve (AUCs) for predicting pulse status with and without CPR on test data were 0.84 and 0.89, respectively. Conclusion: A novel ECG-based algorithm demonstrates potential to improve resuscitation by predicting presence of a spontaneous pulse without pausing CPR.

Download Full-text

Handwritten Digit Recognition Using Different Dimensionality Reduction Techniques

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b1798.078219 ◽

2019 ◽

Vol 8 (2) ◽

pp. 999-1002

Keyword(s):

Principal Component ◽

Training Data ◽

Clear Understanding ◽

Data Set ◽

Linear Discriminant ◽

Digit Recognition ◽

Reduction Techniques ◽

Maximum Variance ◽

Dimensionality Reduction Techniques ◽

Handwritten Digit

The objective of this paper is to introduce to Technologies of linear dimension reduction popularly known as Principal Component Analysis and Linear Discriminant Analysis. PCA reduces the size of data and conserve maximum variance in the form of new variable called principal components where LDA works with minimum class distance and maximizing difference between the classes. Axis of maximum variance is found by PCA while axis of class separability is found by LDA. This method is experimented over and MNIST handwritten digit data set. Our conclusion explains PCA can outperform LDA when training data set a small and recalls values with lesser computational complexity. The present in linear techniques in this paper presents clear understanding and methods in comparative manner

Download Full-text

Real Time Breath Analysis Using Portable Gas Chromatography for Adult Asthma Phenotypes

Metabolites ◽

10.3390/metabo11050265 ◽

2021 ◽

Vol 11 (5) ◽

pp. 265

Author(s):

Ruchi Sharma ◽

Wenzhe Zang ◽

Menglian Zhou ◽

Nicole Schafer ◽

Lesa A. Begley ◽

...

Keyword(s):

Gas Chromatography ◽

Real Time ◽

Rapid Assessment ◽

Principal Component ◽

Corticosteroid Treatment ◽

Breath Analysis ◽

Blood Eosinophil ◽

Exhaled Breath ◽

Respiratory Illnesses ◽

Linear Discriminant

Asthma is heterogeneous but accessible biomarkers to distinguish relevant phenotypes remain lacking, particularly in non-Type 2 (T2)-high asthma. Moreover, common clinical characteristics in both T2-high and T2-low asthma (e.g., atopy, obesity, inhaled steroid use) may confound interpretation of putative biomarkers and of underlying biology. This study aimed to identify volatile organic compounds (VOCs) in exhaled breath that distinguish not only asthmatic and non-asthmatic subjects, but also atopic non-asthmatic controls and also by variables that reflect clinical differences among asthmatic adults. A total of 73 participants (30 asthma, eight atopic non-asthma, and 35 non-asthma/non-atopic subjects) were recruited for this pilot study. A total of 79 breath samples were analyzed in real-time using an automated portable gas chromatography (GC) device developed in-house. GC-mass spectrometry was also used to identify the VOCs in breath. Machine learning, linear discriminant analysis, and principal component analysis were used to identify the biomarkers. Our results show that the portable GC was able to complete breath analysis in 30 min. A set of nine biomarkers distinguished asthma and non-asthma/non-atopic subjects, while sets of two and of four biomarkers, respectively, further distinguished asthmatic from atopic controls, and between atopic and non-atopic controls. Additional unique biomarkers were identified that discriminate subjects by blood eosinophil levels, obese status, inhaled corticosteroid treatment, and also acute upper respiratory illnesses within asthmatic groups. Our work demonstrates that breath VOC profiling can be a clinically accessible tool for asthma diagnosis and phenotyping. A portable GC system is a viable option for rapid assessment in asthma.

Download Full-text

A model for spectroscopic food sample analysis using data sonification

International Journal of Speech Technology ◽

10.1007/s10772-020-09794-9 ◽

2021 ◽

Author(s):

Hsein Kew

Keyword(s):

Dimensionality Reduction ◽

Classification Accuracy ◽

Reduction Method ◽

Real Life ◽

Principal Component ◽

Relevant Information ◽

Analysis Model ◽

Linear Discriminant ◽

Audio Output ◽

Dimensionality Reduction Method

AbstractIn this paper, we propose a method to generate an audio output based on spectroscopy data in order to discriminate two classes of data, based on the features of our spectral dataset. To do this, we first perform spectral pre-processing, and then extract features, followed by machine learning, for dimensionality reduction. The features are then mapped to the parameters of a sound synthesiser, as part of the audio processing, so as to generate audio samples in order to compute statistical results and identify important descriptors for the classification of the dataset. To optimise the process, we compare Amplitude Modulation (AM) and Frequency Modulation (FM) synthesis, as applied to two real-life datasets to evaluate the performance of sonification as a method for discriminating data. FM synthesis provides a higher subjective classification accuracy as compared with to AM synthesis. We then further compare the dimensionality reduction method of Principal Component Analysis (PCA) and Linear Discriminant Analysis in order to optimise our sonification algorithm. The results of classification accuracy using FM synthesis as the sound synthesiser and PCA as the dimensionality reduction method yields a mean classification accuracies of 93.81% and 88.57% for the coffee dataset and the fruit puree dataset respectively, and indicate that this spectroscopic analysis model is able to provide relevant information on the spectral data, and most importantly, is able to discriminate accurately between the two spectra and thus provides a complementary tool to supplement current methods.

Download Full-text