Linear Discriminant Analysis Research Articles

Duets convey information about pair and individual identities in a Neotropical bird

Abstract Vocal individuality is essential for social discrimination but has been poorly studied in animals that produce communal signals (duets or choruses). Song overlapping and temporal coordination make the assessment of individuality in communal signals more complex. Additionally, selection may favor the accurate identification of pairs over individuals by receivers in year-round territorial species with duetting and long-term pair bonding. Here, we studied pair and individual vocal signatures in the polyphonal duets of rufous horneros Furnarius rufus, a Neotropical bird known for its long-term pair bonds. Hornero partners engage in duets to deter territorial intruders and protect their partnership year-round, and can discern duets from neighbors versus strangers. Using a dataset of 471 duets from 43 pairs in two populations, we measured fine-scale acoustic features across different duet levels (e.g., complete duets to non-overlapping syllable parts) and analysis levels (pair or individual). Permuted linear discriminant function analyses classified pairs and individuals more accurately than expected by chance (means: 45% and 47% versus 4 and 2%). Pair identity explained more variance in the multivariate acoustic features of duets than individual or population identities. The initial frequency of the duet showed strong potential for encoding pair identity. The acoustic traits contributing most to individual vocal signatures varied between sexes, which might facilitate the simultaneous assessment of duetters’ identities by receivers. Our study indicates that vocal individuality may exist even in species with intricate and innate communal signals and elucidates the mechanisms employed by horneros in their social discrimination ability.

Type 2 diabetes and susceptibility to COVID-19: a machine learning analysis

BackgroundType 2 diabetes mellitus (T2DM) was one of the most prevalent comorbidities among patients with coronavirus disease 2019 (COVID-19). Interactions between different metabolic parameters contribute to the susceptibility to the virus; thereby, this study aimed to rank the importance of clinical and laboratory variables as risk factors for COVID-19 or as protective factors against it by applying machine learning methods.MethodThis study is a retrospective cohort conducted at a single center, focusing on a population with T2DM. The patients attended the Yazd Diabetes Research Center in Yazd, Iran, from February 20, 2020, to October 21, 2020. Clinical and laboratory data were collected within three months before the onset of the COVID-19 pandemic in Iran. 59 patients were infected with COVID-19, while 59 were not. The dataset was split into 70% training and 30% test sets. Principal Component Analysis (PCA) was applied to the data. The most important components were selected using a ‘sequential feature selector’ and scored by a Linear Discriminant Analysis model. PCA loadings were then multiplied by the PCs’ scores to determine the importance of the original variables in contracting COVID-19.ResultsHDL-C, followed by eGFR, showed a strong negative correlation with the risk of contracting the virus. Higher levels of HDL-C and eGFR offer protection against COVID-19 in the T2DM population. But, the ratio of BUN to creatinine did not show any correlation. Conversely, the AIP, TyG index and TG showed the most positive correlation with susceptibility to COVID-19 in such a way that higher levels of these factors increase the risk of contracting the virus. The positive correlation of diastolic BP, TyG-BMI index, MAP, BMI, weight, TC, FPG, HbA1C, Cr, systolic BP, BUN, and LDL-C with the risk of COVID-19 decreased, respectively.ConclusionThe atherogenic index of plasma, triglyceride glucose index, and triglyceride levels are the most significant risk factors for COVID-19 contracting in individuals with T2DM. Meanwhile, high-density lipoprotein cholesterol is the most protective factor.

EEGER – A Model for Recognition of Human Emotion Using Brain Signal

Emotions significantly impact human thinking, judgment, health, and communication. EEG-based emotion detection has advanced with the use of Brain-Computer Interface (BCI) technology, proving more effective than other physiological data. Despite progress in affective computing, emotion recognition remains a challenge. However, it's increasingly common in brain–machine interfaces, and research shows EEG brain waves are valuable in identifying emotional states. This research introduces a novel automated system for emotion recognition using deep learning techniques on EEG data collected from the GAMEEMO dataset, where participants played emotional assessment games. The system is designed to identify four emotions experienced during gameplay. The proposed model, called EEGER, was trained exclusively on EEG signals and demonstrated a 99.99% accuracy with minimal computational time. Key to its efficiency is the use of LSTM (Long Short-Term Memory) classifiers, which simplify the process by automatically extracting relevant features. The system was tested across different learning rates and epoch values, showing that 10 epochs with a learning rate of 0.0001 were sufficient to achieve the best accuracy. EEGER was also compared with other methods like K-Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA), and Adaptive Boosting (AdaBoost), outperforming them in both accuracy and efficiency. These findings suggest that EEGER offers a promising new approach to EEG-based emotion recognition, optimizing performance with lower complexity and computation time.

A Glycopolymer Sensor Array That Differentiates Lectins and Bacteria.

Identification of bacterial lectins offers an attractive route to the development of new diagnostics, but the design of specific sensors is complicated by the low selectivity of carbohydrate-lectin interactions. Here we describe a glycopolymer-based sensor array which can identify a selection of lectins with similar carbohydrate recognition preferences through a pattern-based approach. Receptors were generated using a polymer scaffold functionalized with an environmentally sensitive fluorophore, along with simple carbohydrate motifs. Exposure to lectins induced changes in the emission profiles of the receptors, enabling the discrimination of analytes using linear discriminant analysis. The resultant algorithm was used for lectin identification across a range of concentrations and within complex mixtures of proteins. The sensor array was shown to discriminate different strains of pathogenic bacteria, demonstrating its potential application as a rapid diagnostic tool to characterize bacterial infections and identify bacterial virulence factors such as production of adhesins and antibiotic resistance.

Effects of Helicobacter pylori and Helicobacter pylori eradication on the microbiota of tongue coating

Eradicating Helicobacter pylori (H. pylori) can cause an imbalance in the microbiota. Dysbiosis of the gut microbiome may produce multiple diseases and bacterial infections. The objective of this study was to investigate the influence of Helicobacter pylori (H. pylori) infection and its eradication on the composition of the oral tongue coating microbiota. A cohort of 35 participants was recruited and categorized into two groups: the H. pylori negative group (N group) consisting of 12 individuals and the H. pylori positive group (23 individuals). Within the H. pylori positive group, subjects were further stratified into the H. pylori pre-eradicated group (HPQ group) and the H. pylori eradicated group (HPH group). H. pylori positive individuals were treated with a quadruple regimen containing bismuth, and tongue coating samples were collected both prior to and following treatment. Concurrently, tongue coating samples were collected from H. pylori negative individuals. High-throughput 16S rRNA sequencing technology was employed to assess the microbial composition of the tongue coating in the N group, HPQ group, and HPH group. Pertinent clinical data were documented.Microbial diversity was found to significantly differ among the N group, HPQ group, and HPH group, as evidenced by variations in Chao1 index, Shannon index, and Partial Least Squares Discriminant Analysis (PLS-DA). The dominant bacterial phyla identified across all groups included Bacteroidetes, Proteobacteria, Firmicutes, Fusobacteria, Actinobacteria, and Saccharibacteria. At the phylum level, Firmicutes exhibited higher relative abundance in the HPQ group in comparison to both the N group and HPH group. Conversely, Bacteroidetes displayed greater prevalence in the N group and HPH group. Linear Discriminant Analysis Effect Size (LEfSe) analysis indicated a higher abundance of Romboutsia, Rothia, and Turiciactor in the HPQ group. Our study revealed significant disparities in microbial diversity and richness among the three groups. Furthermore, our findings suggest a potential association between the presence of Streptococcus, Rothia and H. pylori positive individuals.

Data-Driven Sparse Sensor Placement Optimization on Wings for Flight-By-Feel: Bioinspired Approach and Application.

Flight-by-feel (FBF) is an approach to flight control that uses dispersed sensors on the wings of aircraft to detect flight state. While biological FBF systems, such as the wings of insects, often contain hundreds of strain and flow sensors, artificial systems are highly constrained by size, weight, and power (SWaP) considerations, especially for small aircraft. An optimization approach is needed to determine how many sensors are required and where they should be placed on the wing. Airflow fields can be highly nonlinear, and many local minima exist for sensor placement, meaning conventional optimization techniques are unreliable for this application. The Sparse Sensor Placement Optimization for Prediction (SSPOP) algorithm extracts information from a dense array of flow data using singular value decomposition and linear discriminant analysis, thereby identifying the most information-rich sparse subset of sensor locations. In this research, the SSPOP algorithm is evaluated for the placement of artificial hair sensors on a 3D delta wing model with a 45° sweep angle and a blunt leading edge. The sensor placement solution, or design point (DP), is shown to rank within the top one percent of all possible solutions by root mean square error in angle of attack prediction. This research is the first to evaluate SSPOP on a 3D model and the first to include variable length hairs for variable velocity sensitivity. A comparison of SSPOP against conventional greedy search and gradient-based optimization shows that SSPOP DP ranks nearest to optimal in over 90 percent of models and is far more robust to model variation. The successful application of SSPOP in complex 3D flows paves the way for experimental sensor placement optimization for artificial hair-cell airflow sensors and is a major step toward biomimetic flight-by-feel.

Wheat grain classification using hyperspectral imaging: Concatenating Vis-NIR and SWIR Data for single and bulk grains

Wheat variety identification is an essential component of the official inspection of wheat grains to determine their quality and trade value. Traditionally, wheat class identification requires deep knowledge about the appearance of plants and kernels, their history and distribution. Therefore, there is an urgent need for an automatic technology to standardize the nomenclature of wheat varieties to enable both growers and producers to identify their grains practically. The present study investigated the feasibility of Visible-Near Infrared (Vis-NIR) and Short-Wave Infrared (SWIR) spectral imaging to identify wheat classes. Both sides of the wheat kernel as single kernel measurements and bulk grains were used to acquire hyperspectral data and vertical and horizontal data concatenation was implemented to explore performance differences. In addition, the classification of bulk kernels from single kernel data was investigated. Spectral data was pre-treated by standard normal variate (SNV), Savitzky-Golay first (SG-1) and second derivatives (SG-2) and linear discriminant analysis (LDA), support vector machine (SVM) and artificial neural network (ANN) were applied as the classification algorithms. Furthermore, feature selection was utilised using the minimum redundancy maximum relevance (mRMR) algorithm to investigate the performance difference between data concatenation and feature selection. The results showed that ventral (up) side data showed better classification performances than reverse (down) side data, while Vis-NIR data achieved higher classification accuracies than SWIR data. However, the best classification performance for single kernels was obtained by LDA-SNV using up and down data in the Vis-NIR and SWIR regions vertically and horizontally concatenated with an accuracy of 93.72% for 10-fold cross-validation and 94.93% for test sets. Models based on a hundred features did not achieve the accuracy of models based on concatenated data. Moreover, classification performances of bulk samples were higher than single kernels, which achieved 100% accuracy for both cross-validation and test sets. The study demonstrates that spectral imaging has a high potential to identify wheat classes non-destructively.

Applying Machine Learning and SERS for Precise Typing of DNA Secondary Structures.

Surface-enhanced Raman spectroscopy (SERS) has been demonstrated as an effective method for elucidating secondary structural characteristics of DNA. However, the inherent complexity of the DNA conformation and the lack of SERS samples pose challenges for identifying numerous secondary structures. To address these issues, a synergistic method integrating machine learning with SERS was proposed so as to analyze the SERS spectra of 54 well-defined conformational oligonucleotides, namely, G-quadruplex (G4), i-motif (iM), double-strand (DS), and single-strand (SS) configurations. Principal component analysis (PCA) effectively segregated the oligonucleotides into three distinct conformational groups (G4s, iMs, and others). Furthermore, linear discriminant analysis (LDA), K-nearest neighbor (KNN), and support vector machine (SVM) approaches were utilized to improve the typing accuracy of 54 trained sequences. This enabled the correct classification of the structures of five untrained sequences, as well as the identification of the predominant conformations including G4, iM, and DS formed by two complementary G-rich and C-rich sequences in acidic and neutral pH conditions. The results of this study demonstrated the potential of the proposed methodology for rapid screening and prediction of secondary DNA conformations.

Early metabolic and hemodynamic indicators of kidney dysfunction in mice offspring from parental low protein diet

BackgroundParental malnutrition, particularly a low-protein diet (LPD), causes oligonephropathy at birth and predisposes offspring to hypertension and chronic kidney disease later in life. The onset of adult kidney disease varies based on genetics and environmental factors, often with subclinical alterations in kidney function being overlooked. This study aimed to examine changes in kidney morphology before significant kidney function decline in the offspring of mice fed a low-protein diet.MethodsUsing a combination of histological analysis, kidney metabolic and hemodynamic panel assessments, and advanced statistical techniques such as Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA), we investigated the initial impact of a maternal low-protein diet (LPD) on kidney development and function. Our study utilized 12-week-old F1 mice from F0 parents fed either a low-protein diet (LPD) or a normal-protein diet (NPD) before the onset of hypertension.ResultsThe offspring (F1 generation) of parents (F0 generation) fed an LPD show reduced body weight from birth to P20. The kidney weight was also reduced compared to F1 offspring from parents fed an NPD. At 12 weeks of age, body weight normalized, but kidney weight remained low. Offspring of parents fed an LPD displayed abnormal kidney morphology, including dilated tubules, oligonephropathy, and fluid-filled cysts which had worsened with age. A kidney metabolic panel analysis at 12 weeks revealed a slight but consistent increase in urine albumin, plasma creatinine, mean urea, and BUN concentrations. Although no significant changes in hemodynamic variables were observed, 2/12 mice, both males, showed alterations in systolic blood pressure, suggesting sex-specific effects when comparing F1 mice from F0 fed either diet. Overall, kidney metabolic changes were strongly correlated to parental LPD.ConclusionOur findings indicate that significant kidney damage must accumulate in the F1 generation from parents fed an LPD before any detectable changes in blood pressure occur. Our study suggests that small variations in kidney metabolic function may point to early kidney damage and should not be overlooked in the offspring of these malnourished mice and likely humans.

Beneficial Role of Heat-Treated Lactobacillus sakei HS-1 on Growth Performance, Nutritional Status and Gut Microbiota in Weaned Piglets.

In the swine industry, there is a strong need to replace an antibiotic growth promoter (AGP) used as feed additives in weaned piglets to enhance nutrient utilization in their diets and improve growth performance. Lactobacillus sakei HS-1 strain is a microbial preparation isolated from pickles. The study aim is to investigate the effectiveness of heat-treated L. sakei HS-1 strain (HT-LS) as a growth promoter in weaned piglets compared to colistin (CS), a widely used AGP. Eighteen crossbred weaned piglets (Landrace × Yorkshire × Duroc) of 21 days (average body weight [BW]: 7.06 ± 0.59 kg) were divided into three groups: fed the control diet (CT group), fed a diet supplemented with 30 ppm colistin sulphate (CS group), fed a diet supplemented with HT-LS at a concentration of 2.0 × 105 cells/g (LS group) until 49 days. The results indicated that LS group exhibited significantly higher average daily gain (p < 0.05) and higher BW (p < 0.1) compared with CT group, even higher than CS group. CS group showed higher growth performance compared to CT group but the differences were not statistically significant. In addition, LS group had higher (p < 0.05) or tended to higher (p < 0.1) concentrations of several plasma amino acids than the other two groups at 35 and 49 days. Faecal acetate concentration was higher (p < 0.1) in LS group than in CT group at 35 days. Blood immunoglobulin G concentration in LS group was significantly lower (p < 0.05) than in CT group at 35 and 49 days, and blood immunoglobulin A tended to be lower (p < 0.1) at 35 days than in CT group. LS group showed an increased abundance of g_Prevotella 7, g_Streptococcus and g_Lactobacillus (linear discriminant analysis [LDA] score ≥ 2.0). Predictive metagenomic analysis revealed an enrichment of the mixed acid fermentation pathway (LDA score ≥ 2.0). Furthermore, several gut microbes exhibited correlations with plasma amino acids (p < 0.01) and short-chain fatty acids in faeces (p < 0.01). These findings demonstrate that HT-LS improves the growth performance of weaned piglets by enhancing the efficient utilization of nutrients through gut microbiota modification.

Comparative Evaluation of Machine Learning Models for Mobile Phone Price Prediction: Assessing Accuracy, Robustness, and Generalization Performance

These days, mobile phones are the most commonly purchased goods. Thousands of new models with improved features, designs, and specifications are released yearly. An autonomous mobile price prediction system is required to assist customers in determining whether or not they can afford these devices. Many machine learning models exhibit varying performance degrees based on their architecture and learning properties. Ten widely used classifiers were assessed in this study: Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Decision Tree (DT), Naïve Bayes (NB), Linear Discriminant Analysis (LDA), AdaBoost, and Light Gradient Boosting (LGB). The F1-score, recall, accuracy, and precision of these models were evaluated. According to the findings, the results indicated that LR, with its use of the Elastic Net parameter, outperformed the others with 96% accuracy, 97% precision, 94% recall, and 96% F1-score. Other models like XGBoost, LGB, and SVM also showed strong performance, whereas KNN had the poorest performance. The study highlights the importance of selecting the appropriate model for accurate mobile price prediction. Among all the machine learning used in this paper, the LR classifier outperforms the other state-of-the-art models because of the elastic Net parameter used for mobile phone price prediction.

Discriminant analysis using feature extraction from spectral domain responses to achieve accurate delineation for robust evaluation or classification of soil properties

ABSTRACT Soil spectroscopy offers a method for quantitatively analysing soil chromophores and employing a screening approach. However, utilizing general models with this data at once doesn’t consistently yield accurate results in determining soil parameters. Ambiguities in response within certain domains of the reflectance spectrum are observed. To address this issue, a method is proposed where quantities associated with spectral response are outputted within well-defined domains corresponding to specific parameters. This article introduces a novel approach centred on identifying features from reflectance spectra to assess soil properties and mitigate issues arising from a heterogeneous soil dataset. The focus is on swiftly automating the classification of soil spectral data by extracting features directly related to the varied composition of chromophores in the samples. These features are categorized for each chromophore parameter and analysed using linear discriminant analysis (LDA). The study employs the ‘309 soil samples’ from the GEO-CRADLE open spectral soil library in Greece. Specifically, relevant data from six spectral responses are extracted to separate and quantify certain soil parameters such as clay content, NO3− levels, and SOM (Soil Organic Matter), despite their interrelations. We developed a method to visually represent the determination outcomes quantitatively by establishing three threshold parameter values: 1.6% for SOM, 19% for clay, and 13.6 ppm for NO3−. These determinations will span the explored ranges of ’0.3 to 4.18%’ for SOM, “3 to 48%” for clay, and ’0 to 661.2 ppm’ for NO3−. Utilizing supervised LDA proves notable classification rates of 93.3% for the SOM task, 90% for the Clay task, and 86.6% for NO3− with the specific cut-off value parameter. The final result is presented as a map showing the positions of various prediction samples, highlighting the percentages of clay and organic matter relative to 19% and 1.6%, respectively, as well as the nitrate concentration in these samples relative to 13.6 ppm.

Advanced facial recognition with LBP-URIGL hybrid descriptors

AbstractFacial recognition technology is transformative in security and human-machine interaction, reshaping societal interactions. Robust descriptors, essential for high precision in machine learning tasks like recognition and recall, are integral to this transformation. This paper presents a hybrid model enhancing local binary pattern descriptors for facial representation. By integrating rotation-invariant local binary pattern with uniform rotation-invariant grey-level co-occurrence, employing linear discriminant analysis for feature space optimization, and utilizing an artificial neural network for classification, the model achieves exceptional accuracy rates of 100% for Olivetti Research Laboratory, 99.98% for Maastricht University Computer Vision Test, and 99.17% for Extended Yale B, surpassing traditional methods significantly.

Multi-omics PGT: re-evaluation of euploid blastocysts for implantation potential based on RNA sequencing.

In addition to chromosomal euploidy, can the transcriptome of blastocysts be used as a novel predictor of embryo implantation potential? This retrospective analysis showed that based on differentially expressed genes (DEGs) between euploid blastocysts which resulted and did not result in a clinical pregnancy, machine learning models could help improve implantation rates by blastocyst optimization. Embryo implantation is a multifaceted process, with implantation loss and pregnancy failure related not only to blastocyst euploidy but also to the intricate dialog between blastocyst and endometrium. Although in vitro studies have revealed the characteristics of trophectoderm (TE) differentiation in implanted blastocysts and the function of TE placentation at the implantation site, the precise molecular mechanisms of embryo implantation and their clinical application remain to be fully elucidated. This study involved 102 patients who underwent 111 cycles for preimplantation genetic testing for aneuploidies (PGT-A) between March 2022 and July 2023. The study included 412 blastocysts biopsied at Day 5 [D5] or Day 6 [D6] for patients who underwent PGT-A. The biopsy lysates were split and subjected to DNA and RNA sequencing (DNA- and RNA-seq). One part was used for PGT-A to detect DNA copy number variations, whereas the other part was assessed simultaneously by RNA-seq to determine the transcriptome characteristics. To validate the reliability and accuracy of RNA-seq obtained from this strategy, we initially analyzed the transcriptome of blastocysts with chromosomal aneuploidies. Subsequently, we compared the transcriptomic features of blastocysts with different rates of formation (D5 vs D6) and investigated the network of interactions between key blastulation genes and the receptive endometrium. Then to evaluate the implantation potential of euploid blastocysts, we identified DEGs between euploid blastocysts that resulted in clinical pregnancy (defined as the presence of a gestational sac detected by ultrasound after 5 weeks) and those that did not. These DEGs were then employed to construct a predictive model for optimizing blastocyst selection. The successful detection rate of PGT-A was remarkably high at 99.8%. The RNA data may infer aneuploidy for both trisomy and monosomy. Between the euploid blastocysts that formed on D5 and D6, 187 DEGs were predominantly involved in cell differentiation for embryonic placenta development, the PPAR signaling pathway, and the Notch signaling pathway. These D5/D6 DEGs also exhibited a functional dialog with the receptive phase endometrium-specific genes through protein-protein interaction networks, indicating that the embryo undergoes further differentiation for post-implantation development. Furthermore, a modeling strategy using 280 DEGs between blastocysts leading to successful clinical pregnancies or failing to produce clinical pregnancies was implemented to refine the euploid embryo optimization, achieving areas under the curves of 0.88, 0.71, and 0.84 for the random forest (RF), support vector machine, and linear discriminant analysis models, respectively. Finally, a retrospective analysis of 83 transferred euploid blastocysts using the RF model identified three types of euploid embryos with a decreasing trend in implantation potential. Notably, the implantation rate of the good group was significantly higher than that of the moderate group (88.6% vs 50.0% P = 0.001) and that of the moderate group was higher than that of the poor group (50.0% vs 20.8%, P = 0.035). The sample size was insufficient; thus, a prospective study is needed to verify the clinical effectiveness of the above model. Because we did not analyze blastocysts that led only to biochemical pregnancies but failed clinical pregnancies separately, our classification system still must be modified to screen these embryos. Transcriptomic analysis of blastocysts offers a novel approach for predicting embryo implantation potential, which can be utilized to optimize clinical embryo selection. The ranking system may be effective in reducing the times and costs involved in achieving a clinical pregnancy. This study was funded by the "Pioneer" and "Leading Goose" R&D Program of Zhejiang (No. 2023C03034), the National Natural Science Foundation of China (82101709), and the National Key Research and Development Program for Young Scientists of China (No. 2022YFC2702300). The authors state no competing interests. N/A.

Data-adaptive binary classifiers in high dimensions using random partitioning

Classification in high dimensions has been highlighted for the past two decades since Fisher's linear discriminant analysis (LDA) is not optimal in a smaller sample size n comparing the number of covariates p, i.e. p>n, which is mostly due to the singularity of the sample covariance matrix. Rather than modifying how to estimate the sample covariance and sample mean vector in constructing a classifier, we build two types of high-dimensional classifiers using data splitting, i.e. single data splitting (SDS) and multiple data splitting (MDS). Moreover, we introduce a weighted version of MDS classifier that improves classification performance as illustrated in numerical studies. Each of the split data sets has a smaller size of covariates compared to the sample size so that LDA is applicable, and classification results can be combined with respect to minimizing the misclassification rate. We present theoretical justification backing up our proposed methods by comparing misclassification rates with LDA in high dimension. We also conduct a wide range of simulations and analyse four microarray data sets, which demonstrates that our proposed methods outperform some existing methods or at least yield comparable performances.

Evaluation of urinary volatile organic compounds as a novel metabolomic biomarker to assess chronic kidney disease progression

BackgroundThere is a need to develop accurate and reliable non-invasive methods to evaluate chronic kidney disease (CKD) status and assess disease progression. Given it is recognized that dysregulation in metabolic pathways occur from early CKD, there is a basis in utilizing metabolomic biomarkers to monitor CKD progression. Volatile Organic Compounds (VOCs), a form of metabolomic biomarker, are gaseous products of metabolic processes in organisms which are typically released with greater abundance in disease conditions when there is dysregulation in metabolism. How urinary VOCs reflect the abnormal metabolic profile of patients with CKD status is unknown. Our study aimed to explore this.MethodsIndividuals aged 18–75 years undergoing kidney biopsy were included. Pre-biopsy urine samples were collected. All biopsy samples had an interstitial fibrosis and tubular atrophy (IFTA) grade scored by standardized assessment. Urine supernatant was extracted from residue and sampled for stir bar sorptive extraction followed by Gas chromatography–mass spectrometry (GC-MS) analysis. Post-processing of GC-MS data separated complex mixtures of VOCs based on their volatility and polarity. Mass-to-charge ratios and fragment patterns were measured for individual VOCs identification and quantification. Linear discriminant analysis (LDA) was performed to assess the ability of urinary VOCs in discriminating between IFTA 0 (‘no or minimal IFTA’ i.e. <10%, IFTA), IFTA 1 (‘mild IFTA’ i.e. 10–25% IFTA) and IFTA ≥ 2 (‘moderate or severe IFTA’ i.e. >25% IFTA). Linear regression analysis adjusting for age, sex, estimated glomerular filtration rate, diabetes mellitus (DM) status, and albuminuria was conducted to determine significantly regulated urinary VOCs amongst the groups.Results64 study participants (22 individuals IFTA 0, 15 individuals IFTA 1, 27 individuals IFTA ≥ 2) were included. There were 34 VOCs identified from GC-MS which were statistically associated with correct classification between the IFTA groups, and LDA demonstrated individuals with IFTA 0, IFTA 1 and IFTA ≥ 2 could be significantly separated by their urinary VOCs profile (p < 0.001). Multivariate linear regression analysis reported 4 VOCs significantly upregulated in the IFTA 1 compared to the IFTA 0 group, and 2 VOCs significantly upregulated in the IFTA ≥ 2 compared to the IFTA 1 group (p < 0.05). Significantly upregulated urinary VOCs belonged to one of four functional groups - aldehydes, ketones, hydrocarbons, or alcohols.ConclusionsWe report novel links between urinary VOCs and tubulointerstitial histopathology. Our findings suggest the application of urinary VOCs as a metabolomic biomarker may have a useful clinical role to non-invasively assess CKD status during disease progression.

Effects of Intercropping of Sisal and Three Different Leguminous Plants on Soil Bacterial Diversity

Intercropping is widely utilised in agricultural production to enhance land use efficiency because of its benefits, such as heightened crop productivity and optimised resource utilisation. We investigated the effects of Pinto peanut/sisal (HST), Stylo/sisal (strT) and Grona styracifolia/sisal (JqT) intercropping systems on soil bacterial communities compared with sisal continuous cropping (CK) by using Illumina MiSeq high-throughput sequencing technology. The intercropping system significantly increased the total nitrogen (TN), soil pH and soil moisture levels and decreased the levels of available phosphorus (AP) and available potassium (AK). Minimal variations were observed in Shannon’s and Simpson’s diversity indices between the monoculture and intercropping systems as well as among different intercropping systems. The most abundant phyla observed within the four groups were Proteobacteria, Acidobacteria, Cyanobacteria and Bacteroidetes. At the phylum level, the relative abundances of Proteobacteria, Acidobacteria, Cyanobacteria and Bacteroidetes were 37.37–54.35%, 10.54–21.21%, 3.46–20.43% and 2.15–5.67%, respectively. Compared with ZCK, StrT, JqT and HST treatments led to higher abundance of Cyanobacteria (from 3.46% to 20.43%, 11.37% and 16.58%, respectively) and Bacteroidetes (from 2.15% to 5.67%, 5.21% and 5.10%, respectively). The results of the linear discriminant analysis of effect sizes demonstrated notable variations in the relative abundance of bacterial taxa among various intercropping systems. The dominant categories of the genus in strT and JqT groups were Blastocatellia and Blastocatellaceae-Subgroup4, while Firmicutes was the dominant category of the genus in the HST group. The structure of bacterial communities did not vary between intercropping and monoculture systems. The findings indicated that the impact of the intercropping system on the bacterial community structure was not contingent on the specific intercropping patterns employed.

Leveraging Classifier Performance Using Heuristic Optimization for Detecting Cardiovascular Disease from PPG Signals.

Photoplethysmography (PPG) signals, which measure blood volume changes through light absorption, are increasingly used for non-invasive cardiovascular disease (CVD) detection. Analyzing PPG signals can help identify irregular heart patterns and other indicators of CVD. This research involves a total of 41 subjects sourced from the CapnoBase database, consisting of 21 normal subjects and 20 CVD cases. In the initial stage, heuristic optimization algorithms, such as ABC-PSO, the Cuckoo Search algorithm (CSA), and the Dragonfly algorithm (DFA), were applied to reduce the dimension of the PPG data. Next, these Dimensionally Reduced (DR) PPG data are then fed into various classifiers such as Linear Regression (LR), Linear Regression with Bayesian Linear Discriminant Classifier (LR-BLDC), K-Nearest Neighbors (KNN), PCA-Firefly, Linear Discriminant Analysis (LDA), Kernel LDA (KLDA), Probabilistic LDA (ProbLDA), SVM-Linear, SVM-Polynomial, and SVM-RBF, to identify CVD. Classifier performance is evaluated using Accuracy, Kappa, MCC, F1 Score, Good Detection Rate (GDR), Error rate, and Jaccard Index (JI). The SVM-RBF classifier for ABC PSO dimensionality reduced values outperforms other classifiers, achieving the highest accuracy of 95.12% along with the minimum error rate of 4.88%. In addition to that, it provides an MCC and kappa value of 0.90, a GDR and F1 score of 95%, and a Jaccard Index of 90.48%. This study demonstrated that heuristic-based optimization and machine learning classification of PPG signals are highly effective for the non-invasive detection of cardiovascular disease.

Preparation and Characterization of PLA-Based Films Fabricated with Different Citrus Species Peel Powder

The present study aimed to investigate whether different citrus peel powders (orange, mandarin, and lemon) could be incorporated into polylactic acid (PLA), for the preparation and characterization of biodegradable films made of this fruit waste. In particular, films were prepared by the solvent casting method and tested in terms of physicochemical and biochemical parameters, along with mechanical properties. Furthermore, the citrus peel powders were tested for their physicochemical and biochemical properties after ethanolic extraction. The results showed that the addition of citrus powders into PLA proved to be efficient compared to the control films (PLA). The citrus peel-based films showed high antioxidant capacity (38.37%–32.54%), a considerable total phenolic content (17.2–12.58 mg GAE/L), good lightness (L*: 42.83–41.93), elastic Young’s modulus (257.95–175.38 MPa), oxygen transmission rate (976.5 mL m−2 day−1–1218 mL m−2 day−1), elongation at break (183.06%–135.95%), and tensile strength (6.15–4.56 MPa), which were affected significantly (p &lt; 0.05) by the botanical origin of citrus peel. Concerning the citrus peel extracts, the highest values in antioxidant capacity (52.56%), total phenolic content (724.8 mg GAE/L), and titratable acidity (714.67 mg of citric acid/L) were recorded in the extract of lemon peel powders. The corresponding values for orange peel powder extracts were 39.43%, 563.8 mg GAE/L, and 576 mg of citric acid/L, while those for mandarin were 33.01%, 558.46 mg GAE/L, and 54.67 mg of citric acid/L. The application of multivariate analysis of variance and linear discriminant analysis on the mechanical properties, physicochemical, and biochemical data resulted in the differentiation of pure PLA and PLA-based films fabricated with citrus peel powder. From the above findings, it is concluded that citrus peel powders are sources of phytochemicals and can be used for the preparation of PLA-based films for potential applications in food preservation.

Enhancing the accuracy of blockage detection in centrifugal pump using the majority voting classifier on an unbalanced dataset

Blockage in a centrifugal pump can adversely impact its performance. In this study, an experimental facility is developed to simulate three types of blockages (suction, discharge, and simultaneous suction and discharge). To classify these faults and detect their severity, a methodology involving the application of majority voting classifier (MVC) to the pump’s discharge pressure signals is presented. An unbalanced dataset is constructed, where the number of samples for a specific blockage condition decreases with increasing fault severity. Statistical features, entropy features, and entropies meta features are extracted from the signal and ranked using XGBoost and minimum redundancy maximum relevance (MRMR). Subsequently, the optimal features are selected based on the best performing model (Linear Discriminant Analysis) among ten different models. Best four models are selected and ensembled to form MVC. Results show that MVC achieves an accuracy of 89.90% and 88.26% for features selected by XGBoost and MRMR, respectively. Finally, the unbalanced dataset is balanced using synthetic minority oversampling and it is shown that MVC achieves an accuracy of 100% on this balanced dataset for the features selected using both approaches.