Fisher Ratio Research Articles

The analysis of the prognostic value of the neutrophil/ lymphocyte ratio and the platelet/lymphocyte ratio among advanced endometrial cancer patients.

About 20% of endometrial cancer (EC) patients have advanced disease (FIGO III & IV) at the moment of diagnosis. An attempt to evaluate the prognostic value of biochemical markers of inflammation and classic endometrial cancer prognostic factors in the group of advanced EC (aEC) patients has been made in this study. Records of 266 patients treated in the Maria Sklodowska-Curie Memorial Cancer Centre and Institute of Oncology, Cracow Branch between the year 2006 and 2018 were included in the study. Follow-up ranged from 1 to 138 months. Progression free survival (PFS) and overall survival (OS) have been set as endpoints. Tests such as: chi-squared, Fisher, log-rank, Mann-Whitney, Kruskal-Wallis and Cox proportional hazard ratio were used in the statistical analyses. In the analysed group high total platelet count (PLT) before operative treatment and high levels of white blood cells (WBC), PLT, neutrophil/lymphocyte ratio (NLR) and platelet/lymphocyte ratio (PLR) before adjuvant therapy (AT) have been significantly associated with shorter PFS and OS. After setting the cut-off values of NLR and PLR a statistically significant correlation between those parameters and PFS as well as OS has been shown. Multivariate analysis has indicated that NLR is an independent prognostic factor of the course of aEC. NLR and PLR correlate significantly with OS and PFS in aEC. NLR is an independent prognostic factor in this group. It is possible to distinguish 3 risk groups, among aEC patients, based on NRL and PLR.

Sensitization to Aspergillus Mix Among Atopic Sickle Cell Disease Patients in Abidjan, Côte d’Ivoire

The objective of this study was to determine the epidemiological characteristics of sensitization to Aspergillus in these atopic sickle cell patients who present respiratory disorders unrelated to taking NSAIDs. This is a prospective study with a descriptive and analytical aim which was conducted at the University Hospital Center (CHU) of Cocody (Abidjan). It took place from September 2017 to May 2018 on 117 atopic sickle cell disease patients, with no known history of allergy to aeroallergens, to any foods or to occupational allergens. These patients were interviewed and clinically examined for an atopic site. They were subsequently subjected to skin tests. Statistical analyzes were performed using Epi info 6.0 software using Fisher's test and odds ratio. The significance level was located at an odds ratio greater than 1. The comparison of the percentages was carried out by Fisher's test with a significance level p = 0.05. The majority of patients with sensitization to Aspergillus mix were over 15 years of age, with a predominance of women (Sex ratio: 0.56). Neither sex nor age appeared to influence the state of sensitization in our study (p> 0.05). The overall prevalence of sensitization to Aspergillus mix was 7.7%. Our results correlated asthma severity with sensitization to Aspergillus mix (p<0.05). However, there was no significant correlation between severity of allergic rhinitis and sensitization to Apergillus mix. This study confirms the low prevalence of sensitization to Aspergillus mix. Allergy to Aspergillus mix is an uncommon phenomenon in sickle cell patients but its monitoring in this population should be given special attention as it is subject to many complications.

Control-Normalized Fisher Ratio Analysis of Comprehensive Two-Dimensional Gas Chromatography Time-of-Flight Mass Spectrometry Data for Enhanced Biomarker Discovery in a Metabolomic Study of Orthopedic Knee-Ligament Injury.

An innovative form of Fisher ratio (F-ratio) analysis (FRA) is developed for use with comprehensive two-dimensional gas chromatography/time-of-flight mass spectrometry (GC × GC-TOFMS) data and applied to the investigation of the changes in the metabolome in human plasma for patients with injury to their anterior cruciate ligament (ACL). Specifically, FRA provides a supervised discovery of metabolites that express a statistically significant variance in a two-sample class comparison: patients and healthy controls. The standard F-ratio utilizes the between-class variance relative to the pooled within-class variance. Because standard FRA is adversely impacted by metabolites expressed with a large within-class variance in the patient class, "control-normalized FRA" has been developed to provide complementary information, by normalizing the between-class variance to the variance of the control class only. Thirty plasma samples from patients who recently suffered from an ACL injury, along with matched controls, were subjected to GC × GC-TOFMS analysis. Following both standard and control-normalized FRA, the concentration ratio for the top 30 "hits" in each comparison was obtained and then t-tested for statistical significance. Twenty four out of 30 metabolites plus the therapeutic agent, naproxen (24/30), passed the t-test for the control-normalized FRA, which included 8/24 unique to control-normalized FRA and 16/24 in common with the standard FRA. Likewise, standard FRA provided 21/30 metabolites passing the t-test, with 5/21 undiscovered by control-normalized FRA. The complementary information obtained by both F-ratio analyses demonstrates the general utility of the new approach for a variety of applications.

COMPARISON OF PHARMACISTS PROFESSIONAL ACTIVITY OF UKRAINIAN PHARMACY ON PROVISION OF INFORMATION ON ADVERSE REACTIONS OF PHARMACEUTICAL PRODUCTS

The aim of the research is the comparison of professional activity of pharmacists of pharmaceutical institution in Ukraine with different education level in relation to their responsibilities in detection and prevention of adverse reactions (AR) or lack of efficacy of pharmaceutical products (PP), set out in the regulatory documentation on this matter. Materials and methods. The questionnaire was developed and used for pharmacists of pharmaceutical institution, taken training on cycles of postgraduate education during 2016–2018. 70 higher education pharmacists (HEPs) and 80 specialized secondary education pharmacists (SSEP) were inquired. The integrity was evaluated by Fisher's ratio test (F). For convenience of calculation the corresponding functions of MS Excel were used. Results. The majority of SSEPs and HEPs of Ukrainian pharmaceutical institutions are aware of their duty to provide information on AR or lack of efficacy of pharmaceutical products to the Department of Post-authorization Supervision of the State Expert Center of the Ministry of Health of Ukraine and are aware of the regulatory legal documentation on this issue, however they are not active enough to take necessary action filling in the “Adverse drug reaction reporting form” and sending it to the national department. One of the reasons for the underactivity of pharmacy workers, irrespective of their level of education, is the low organization of this process in pharmacy institutions, in particular the absence of the “Adverse drug reaction reporting forms”. Conclusion. Higher education pharmacist are more self-acting in completing “Adverse drug reaction reporting forms” and are less likely to shift their responsibilities to the pharmacy manager. It is critical to resolve the issue on enhancement of efficiency of detecting AR and/or lack of efficacy of PP in pharmacy institutions of Ukraine is to improve the quality of organizational work of pharmacy managers.

Identification of Diagnostic Biomarkers and Subtypes of Liver Hepatocellular Carcinoma by Multi-Omics Data Analysis.

As liver hepatocellular carcinoma (LIHC) has high morbidity and mortality rates, improving the clinical diagnosis and treatment of LIHC is an important issue. The advent of the era of precision medicine provides us with new opportunities to cure cancers, including the accumulation of multi-omics data of cancers. Here, we proposed an integration method that involved the Fisher ratio, Spearman correlation coefficient, classified information index, and an ensemble of decision trees (DTs) for biomarker identification based on an unbalanced dataset of LIHC. Then, we obtained 34 differentially expressed genes (DEGs). The ability of the 34 DEGs to discriminate tumor samples from normal samples was evaluated by classification, and a high area under the curve (AUC) was achieved in our studied dataset and in two external validation datasets (AUC = 0.997, 0.973, and 0.949, respectively). Additionally, we also found three subtypes of LIHC, and revealed different biological mechanisms behind the three subtypes. Mutation enrichment analysis showed that subtype 3 had many enriched mutations, including tumor protein p53 (TP53) mutations. Overall, our study suggested that the 34 DEGs could serve as diagnostic biomarkers, and the three subtypes could help with precise treatment for LIHC.

Prevalência de extubação não planejada e fatores associados em uma unidade de terapia intensiva neonatal

INTRODUÇÃO: Intubação endotraqueal é procedimento comum nas Unidades de Terapia Intensiva Neonatais e tem como evento adverso a extubação não planejada, um incidente grave, associado a morbidade neonatal. OBJETIVO: Verificar a prevalência de extubação não planejada e fatores associados em recém-nascidos submetidos à ventilação mecânica na unidade de terapia intensiva neonatal por condições respiratórias, cardíacas ou por pós-operatório. MATERIAIS E MÉTODOS: Estudo transversal, retrospectivo realizado entre março a dezembro de 2017. Os dados foram coletados da ficha de notificação do serviço e incluíram: sexo, peso no momento do evento, comorbidades do paciente, data e hora de ocorrência, condições associadas e conduta pós-extubação. RESULTADOS: Em 38 recém-nascidos em ventilação mecânica foram registrados 72 eventos, a prevalência da extubação não planejada de 4,6%. Entre os fatores identificados, peso inferior a 1.500g foi observado em 20 recém-nascidos (52,6%) e prematuridade em 25 (65,8%). Em 15 recém-nascidos (39,5%) houve mais de um evento/paciente. Peso inferior a 2.500g esteve associado a um risco 6 vezes maior de recorrência do incidente. As condições associadas aos eventos foram agitação motora do recém-nascido (50%), manuseio da cânula endotraqueal (28,3%) e durante procedimentos de rotina do recém-nascido (21,7%). Reintubação foi necessária em 58 casos (80,5%), sendo imediata em 20 (34,5%). CONCLUSÃO: A agitação motora e o manuseio da cânula endotraqueal, portanto, foram os fatores mais associados aos eventos, a recorrência foi mais frequente em recém-nascido com peso inferior a 2.500g. Medidas de prevenção devem incluir o manejo adequado da agitação motora do recém-nascido e implementação de protocolos de manuseio da cânula endotraqueal.

Statistical inference of mass channel purity from Fisher ratio analysis using comprehensive two-dimensional gas chromatography with time of flight mass spectrometry data.

Tile-based Fisher ratio (F-ratio) analysis has recently been developed and validated for discovery-based studies of highly complex data collected using comprehensive two-dimensional gas chromatography coupled with time-of-flight mass spectrometry (GC×GC-TOFMS). In previous studies, interpretation and utilization of F-ratio hit lists has relied upon manual decomposition and quantification performed by chemometric methods such as parallel factor analysis (PARAFAC), or via manual translation of the F-ratio hit list information to peak table quantitative information provided by the instrument software (ChromaTOF). Both of these quantification approaches are bottlenecks in the overall workflow. In order to address this issue, a more automatable approach to provide accurate relative quantification for F-ratio analyses was investigated, based upon the mass spectral selectivity provided via the F-ratio spectral output. Diesel fuel spiked with 15 analytes at four concentration levels (80, 40, 20, and 10ppm) produced three sets of two class comparisons that were submitted to tile-based F-ratio analysis to obtain three hit lists, with an F-ratio spectrum for each hit. A novel algorithm which calculates the signal ratio (S-ratio) between two classes (eg., 80ppm versus 40ppm) was applied to all mass channels (m/z) in the F-ratio spectrum for each hit. A lack of fit (LOF) metric was utilized as a measure of peak purity and combined with F-ratio and p-values to study the relationship of each of these metrics with m/z purity. Application of a LOF threshold coupled with a p-value threshold yielded a subset of the most pure m/z for each of the 15 spiked analytes, evident by the low deviations (< 5%) in S-ratio relative to the true concentration ratio. A key outcome of this study was to demonstrate the isolation of pure m/z without the need for higher level signal decomposition algorithms.

Investigating different stress-relief methods using Electroencephalogram (EEG).

Mental stress is a prevalent issue in the modern society and a prominent contributing factor to various physical and psychological diseases. This paper investigates the feasibility of detecting different stress levels using electroencephalography (EEG), and evaluates the effectiveness of various stress-relief methods. EEG data were collected from 25 subjects while they were at rest and under 3 different levels of stress induced by mental arithmetic tasks. Nine features that correlate with stress from existing literature were extracted. Subsequently, discriminative features were selected by Fisher Ratio and used to train a Linear Discriminant Analysis classifier. Results from 10-fold cross-validation yielded averaged intra-subject classification accuracy of 85.6% for stress versus rest, 7l.2% for two levels of stress and rest, and 58.4% for three levels of stress and rest. The results showed high promise of using EEG to detect level of stress, and the features selected showed that Beta brain waves (13-30HZ) and prefrontal relative Gamma power are most discriminative. Five different stress-relief methods were then evaluated, and the method of hugging a pillow was found to be the most effective measure relatively in decreasing the stress level detected using EEG. These results show promise of future research in real-time stress detection and reduction using EEG for stress management and relief.

Cloud Point Extraction in Presence of Multi-walled Carbon Nanotubes for Removal of Direct Green 26 from Aqueous Solutions: Optimization by Box-Behnken Design and Desirability Functions

The novel approach of cloud point extraction in the presence of multi-walled carbon nanotubes (CPE/MWCNTs) is presented for removal of Direct Green 26 (DG26) from aqueous solutions. The experiments were conducted based on the Box-Behnken experimental design and the removal process was optimized by the response surface modeling and desirability function (DF) approach. Effects of the experimental variables (MWCNTs amount, solution pH, clouding time and volume of Triton X-100 solution) on the process efficiency were modeled using a quadratic equation with the coefficient of determination (R2) value of 0.9944 and Fisher ratio of 177.07. Using the DF approach, optimum levels of the variables determined as MWCNTs amount of 0.7 mg, pH 3, clouding time of 40 min and Triton X-100 solution volume of 993 µL. Experimental checking of the conditions resulted in the dye removal efficiency of 95.86%. Results of the study proved the applicability of the proposed method for DG26 removal from real water samples.

Discovery-based analysis and quantification for comprehensive three-dimensional gas chromatography flame ionization detection data

Basic principles are introduced for implementing discovery-based analysis with automated quantification of data obtained using comprehensive three-dimensional gas chromatography with flame ionization detection (GC3-FID). The GC3-FID instrument employs dynamic pressure gradient modulation, providing full modulation (100% duty cycle) with a fast modulation period (PM) of 100 ms. Specifically, tile-based Fisher-ratio analysis, previously developed for comprehensive two-dimensional gas chromatography with time-of-flight mass spectrometry (GC×GC-TOFMS), is adapted and applied for GC3-FID where the third chromatographic dimension (3D) is treated as the “spectral” dimension. To evaluate the instrumental platform and software implementation, ten “non-native” compounds were spiked into a ninety-component base mixture to create two classes with a concentration ratio of two for the spiked analyte compounds. The Fisher ratio software identified 95 locations of potential interest (i.e., hits), with all ten spiked analytes discovered within the top fourteen hits. All 95 hits were quantified by a novel signal ratio (S-ratio) algorithm portion of the F-ratio software, which determines the time-dependent S-ratio of the 3D chromatograms from one class to another, thus providing relative quantification. The average S-ratio for spiked analytes was 1.94 ± 0.14 mean absolute error (close to the nominal concentration ratio of two), and 1.06 ± 0.16 mean absolute error for unspiked (i.e., matrix) components. The appearance of the S-ratio as a function of 3D retention time in the GC3 dataset, referred to as an S-ratiogram, provides indication of peak purity for each hit. The unique shape of the S-ratiogram for hit 1, α-pinene, suggested likely 3D overlap. Parallel factor analysis (PARAFAC) decomposition of the hit location confirmed that overlap was occurring and successfully decomposed α-pinene from a highly overlapped (3Rs = 0.1) matrix interferent.

Adaptive dictionary learning based on local configuration pattern for face recognition

Sparse representation based on classification and collaborative representation based classification with regularized least square has been successfully used in face recognition. The over-completed dictionary is crucial for the approaches based on sparse representation or collaborative representation because it directly determines recognition accuracy and recognition time. In this paper, we proposed an algorithm of adaptive dictionary learning according to the inputting testing image. First, nearest neighbors of the testing image are labeled in local configuration pattern (LCP) subspace employing statistical similarity and configuration similarity defined in this paper. Then the face images labeled as nearest neighbors are used as atoms to build the adaptive representation dictionary, which means all atoms of this dictionary are nearest neighbors and they are more similar to the testing image in structure. Finally, the testing image is collaboratively represented and classified class by class with this proposed adaptive over-completed compact dictionary. Nearest neighbors are labeled by local binary pattern and microscopic feature in the very low dimension LCP subspace, so the labeling is very fast. The number of nearest neighbors is changeable for the different testing samples and is much less than that of all training samples generally, which significantly reduces the computational cost. In addition, atoms of this proposed dictionary are these high dimension face image vectors but not lower dimension LCP feature vectors, which ensures not only that the information included in face image is not lost but also that the atoms are more similar to the testing image in structure, which greatly increases the recognition accuracy. We also use the Fisher ratio to assess the robustness of this proposed dictionary. The extensive experiments on representative face databases with variations of lighting, expression, pose, and occlusion demonstrate that the proposed approach is superior both in recognition time and in accuracy.

A new BAT optimization algorithm based feature selection method for electrocardiogram heartbeat classification using empirical wavelet transform and Fisher ratio

In this paper, a novel feature selection method is proposed for the categorization of electrocardiogram (ECG) heartbeats. The proposed technique uses the Fisher ratio and BAT optimization algorithm to obtain the best feature set for ECG classification. The MIT-BIH arrhythmia database contains sixteen classes of the ECG heartbeats. The MIT-BIH ECG arrhythmia database divided into intra-patient and inter-patient schemes to be used in this study. The proposed feature selection methodology works in following steps: firstly, features are extracted using empirical wavelet transform (EWT) and then higher-order statistics, as well as symbolic features, are computed for each decomposed mode of EWT. Thereafter, the complete feature vector is obtained by the conjunction of EWT based features and RR interval features. Secondly, for feature selection, the Fisher ratio is utilized. It is optimized by using BAT algorithm so as to have maximal discrimination of the between classes. Finally, in the classification step, the k-nearest neighbor classifier is used to classify the heartbeats. The performance measures i.e., accuracy, sensitivity, positive predictivity, specificity for intra-patient scheme are 99.80%, 99.80%, 99.80%, 99.987% and for inter-patient scheme are 97.59%, 97.589%, 97.589%, 99.196% respectively. The proposed feature selection technique outperforms the other state of art feature selection methods.

Pharmacophore modelling, QSAR study, molecular docking and insilico ADME prediction of 1,2,3-triazole and pyrazolopyridones as DprE1 inhibitor antitubercular agents

Tuberculosis (TB) is a chronic lung infected airborne disease caused by Mycobacterium tuberculosis (MTB). The development of resistance towards available antitubercular agents leads to the discovery of new drugs for treatment against these resistant bacteria. Decaprenyl phosphoryl-β-D-Ribose 20-epimerase (DprE1) is a vulnerable target for the design of antitubercular agents which are more acting against multidrug resistant bacterial pathogens. DprE1 is an oxidase involved in the synthesis of arabinogalactan. Inhibition of DprE1 leads to blocking off cell wall synthesis, causing the death of the bacteria. A series of 50 DprE1 inhibitors having activity were subjected to 2D, 3D QSAR, Pharmacophore Modeling, Molecular Docking and in silico ADME studies. Prediction of preliminary Pharmacokinetic and the Drug Likeliness profile was performed for these compounds by in silico ADME study. 2D-QSAR and 3D- QSAR models developed by Partial Least Square associated with the Sphere Exclusion method (PLS-SE) and StepWise variable selection method (SW-kNN MFA) based on k- Nearest Neighbor technique are more significant which have cross-validated squared correlation coefficient (q2), coefficient of determination (r2), Fisher ratio (F) values as 0.7499, 0.8917 and 85.04 and the internal (q2 = 0.8198), external (pred_r2 = 0.6109) model validation correctly predicts activity ~ 81% and ~ 61% for the training and test set, respectively. Pharmacophore model was developed with two aromatic regions (Aro), one aliphatic (Ala) and one hydrogen donor (HDr). Docking studies of the selected inhibitors with the active site of DprE1 enzyme showed hydrogen bond interaction with Gly-116, His-131, Arg-118, Thr-117 and Gln-299 residues present at the active site. The results of the present work provide more useful information and important structural insights for designing DprE1 inhibitors with much more enhanced potency.

Biometric Identification Method for Heart Sound Based on Multimodal Multiscale Dispersion Entropy.

In this paper, a new method of biometric characterization of heart sounds based on multimodal multiscale dispersion entropy is proposed. Firstly, the heart sound is periodically segmented, and then each single-cycle heart sound is decomposed into a group of intrinsic mode functions (IMFs) by improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN). These IMFs are then segmented to a series of frames, which is used to calculate the refine composite multiscale dispersion entropy (RCMDE) as the characteristic representation of heart sound. In the simulation experiments I, carried out on the open heart sounds database Michigan, Washington and Littman, the feature representation method was combined with the heart sound segmentation method based on logistic regression (LR) and hidden semi-Markov models (HSMM), and feature selection was performed through the Fisher ratio (FR). Finally, the Euclidean distance (ED) and the close principle are used for matching and identification, and the recognition accuracy rate was 96.08%. To improve the practical application value of this method, the proposed method was applied to 80 heart sounds database constructed by 40 volunteer heart sounds to discuss the effect of single-cycle heart sounds with different starting positions on performance in experiment II. The experimental results show that the single-cycle heart sound with the starting position of the start of the first heart sound (S1) has the highest recognition rate of 97.5%. In summary, the proposed method is effective for heart sound biometric recognition.

A Novel EEG Correlation Coefficient Feature Extraction Approach Based on Demixing EEG Channel Pairs for Cognitive Task Classification

This paper presents a novel feature extraction method for electroencephalogram (EEG)-based cognitive task classification based on the correlation coefficients of EEG channel pairs by introducing preprocessing of the EEG signals. The preprocessing attempts to optimally demix each pair of EEG channels using a two-dimensional rotation matrix in order to mitigate the interference between channel pairs and, consequently, to enhance the resulting correlation coefficient features for cognitive task classification. For the optimization, the following criteria are proposed with an optimal rotation angle approximated for each criterion: $i$ ) maximum inter-class correlation coefficient distance (ICCD); $ii$ ) minimum within-class correlation coefficient distance (WCCD); and $iii$ ) maximum Fisher ratio (FR), which is the ratio of ICCD to WCCD. Performance evaluation based on the cognitive task dataset, dataset IV and Ib in BCI competition II, and Keirn and Aunon’s dataset, shows that ICCD optimization with the ‘above the mean’ and 1.5 interquartile range (IQR) feature selection method yields the best classification performance in comparison with other existing cognitive task classification methods.

Flavor volatiles evolution of Chinese horse bean-chili-paste during ripening, accessed by GC×GC-TOF/MS and GC-MS-olfactometry

ABSTRACT The evolution of volatile compounds during the ripening of Chinese horse bean-chili-paste (CHCP) was investigated in this study. GC×GC-TOF/MS allowed an identification of 748 volatiles in three CHCP samples, respectively, ripened for 3 months (M3), 12 months (M12) and 24 months (M24), and it showed that a longer ripening resulted in a richer diversity of the volatiles. In addition, M3 contained more aldehydes and organic acids in content and M12 had more alcohols, ketones, and esters, while M24 was abundant in heterocyclics. A total of 69 among the 748 volatiles were discriminated as the key flavor compounds of CHCP by method of Fisher ratio together with odor activity value and flavor dilution, including 12 alcohols, 9 aldehydes, 4 ketones, 5 organic acids, 16 esters, 4 phenols, 6 sulfur-containing compounds, and 13 heterocyclics. Further, principal component analysis suggested that some key aldehydes contributed the flavor of M3, while some key alcohols, esters and heterocyclics existed in M12, and some key phenols and heterocyclics were in M24. Varying of the key flavor volatiles during CHCP ripening gave it different fragrance configurations. Results presented details for the volatile profiles of CHCP during the natural ripening period, beneficial to shorten fermentation time by functional microorganisms, and could enrich the desire flavors.

Modified QuEChERS extraction for the analysis of young-of-year smallmouth bass using GC × GC-TOFMS.

Signs of disease, such as external lesions, have been prevalent in smallmouth bass throughout the Susquehanna River Basin, USA. Previous targeted chemical studies in this system have identified known persistent organic pollutants, but a common explanatory link across multiple affected sites remains undetermined. A fast and robust extraction method that can be applied to young-of-year fish is needed to effectively screen for target and non-target compounds that may be impacting organism health. The quick, easy, cheap, effective, rugged, and safe (QuEChERS) extraction methodology was optimized to perform both targeted and non-targeted chemical analyses from a single extraction of whole young-of-year fish. Comprehensive two-dimensional gas chromatography coupled with time-of-flight mass spectrometry (GC × GC-TOFMS) was used for extract analysis. Sample extraction was performed using the solvent ethyl acetate, followed by a two-step cleanup in which samples were frozen for lipid removal and subjected to dispersive solid phase extraction using Florisil. A sample of 21 young-of-year smallmouth bass collected from areas with disease and exhibiting different types of external lesions were evaluated for 233 target compounds. A total of 34 organic contaminants, including polychlorinated biphenyls, brominated diphenyl ethers, organochlorinated pesticides, and personal care products, were detected. Data from this sample set was then analyzed for non-targets. Using the Fisher ratio method and multivariate analysis, an additional 10 significant features were identified specific to either fish with visible lesions or with no visible disease characteristics.

Non-targeted discovery-based analysis for gas chromatography with mass spectrometry: A comparison of peak table, tile, and pixel-based Fisher ratio analysis

The ability to discover minute differences between samples or sample classes for gas chromatography coupled to mass spectrometry (GC-MS) can be a challenging endeavor, especially when those differences are not a priori. Fisher ratio (F-ratio) analysis is an apt technique to probe the differences between GC-MS chromatograms. F-ratio analysis is a supervised, non-targeted, discovery-based method that compares two different samples (or sample classes) to reduce the GC-MS dataset into a hit list composed of class distinguishing compounds. Three different F-ratio techniques, peak table, tile, and pixel-based were used to “discover” nine non-native analytes that were spiked into gasoline at four different nominal concentrations of 250, 85, 25, 5 parts-per-million (ppm). For the tile and pixel-based F-ratio calculations, a novel methodology is introduced to improve the sensitivity of the F-ratio calculations while reducing false positives. Furthermore, we use a combinatorial technique using null class comparisons, termed null distribution analysis, to determine a statistical F-ratio cutoff for analysis of the hit lists. The pixel-based algorithm was the most sensitive method and was able to “discover” all nine spiked analytes at a nominal concentration of 250 ppm albeit with one false positive interspersed towards the bottom of the hit list. The pixel-based software was also able to “discover” more of the spiked analytes at the lower concentrations with seven of the spiked analytes “discovered” at 85 ppm, four of the spiked analytes “discovered” at 25 ppm, and one analyte “discovered” at 5 ppm.

MsCNN: A Deep Learning Framework for P300-Based Brain–Computer Interface Speller

In this paper, a novel multiscale convolutional neural network (MsCNN) architecture is proposed for P300 based BCI speller. Major limitation of BCI system is that it requires a large number of data to train the system. However, collection of large amount of data from a single subject makes the task tedious for the subject and this will affect the quality of the acquired electroencephalogram (EEG) signal. To cope with this issues, a MsCNN model with transfer learning (MsCNN-TL) technique is proposed in this work for improvement of the P300 based character recognition performance with limited amount of training data. The multi-resolution deep features are extracted from the fully connected layer of the trained MsCNN-TL architecture. These deep features are optimized using Fisher ratio ( F-ratio ) based feature selection technique and the optimal features are applied to the ensemble of support vector machines (ESVMs) for P300 detection. The proposed method is tested on BCI competition datasets and it achieves better performance compared to the other state-of-the-art techniques for limited training dataset.

Classification of Motor Imagery Using a Combination of User-Specific Band and Subject-Specific Band for Brain-Computer Interface

The essential task of a Brain-Computer Interface (BCI) is to extract the motor imagery features from Electro-Encephalogram (EEG) signals for classifying the thought process. It is necessary to analyse these obtained signals in both the time domain and frequency domains. It is observed that the combination of multiple algorithms increases the performance of the feature extraction process. This paper identifies combinations that have not been attempted previously and improves the accuracy of the overall process, although other authors implemented different combinations of the techniques. The focus is given more on the feature extraction process and frequency bands, which are user-specific and subject-specific frequency bands. In both time and frequency domains, after analysing EEG signals with the time domain parameter, we select the frequency band and the timing while using the Fisher ratio of the time domain parameter (TDP). We used Fisher discriminant analysis (FDA)-type F-score to simultaneously select the frequency band and time segment for multi-class classification. We extracted subject-specific TDP features from the training trials to train the classifier when optimal time-frequency areas were selected for each subject. In this paper, various methods are explored for obtaining the features, which are Time Domain Parameters (TDP), Fast Fourier Transform (FFT), Principal Component Analysis (PCA), R2, Fast Correlation Based Filter (FCBF), Empirical Mode Decomposition (EMD), and Intrinsic time-scale decomposition (ITD). After the extraction process, PCA is used for dimensionality reduction. An efficient result was obtained with the combination of TDP, FFT, and PCA. We used the multi-class Fisher’s linear discriminant analysis (LDA) as the classifier, which was in line with the FDA-type F-score. It is observed that the combination of feature extraction techniques to the frequency bands that were selected by the Fisher ratio and FDA type F-score along with Fisher’s LDA classifier had higher accuracy than the results obtained other researches. A kappa coefficient accuracy of 0.64 is obtained for the proposed technique. Our method leads to better classification performance when compared to state-of-the-art methods. The novelty of the approach is based on the combination of frequency bands and two feature extraction methods.