Analysis Algorithm Research Articles

Prediction and clustering of Alzheimer’s disease by race and sex: a multi-head deep-learning approach to analyze irregular and heterogeneous data

Early detection of Alzheimer’s disease (AD) is crucial to maximize clinical outcomes. Most disease progression analyses include people with diagnoses of cognitive impairment, limiting understanding of AD risk among those with normal cognition. The objective was to establish AD progression models through a deep learning approach to analyze heterogeneous, multi-modal datasets, including clustering analyses of population subsets. A multi-head deep-learning architecture was built to process and learn from biomedical and imaging data from the National Alzheimer’s Coordinating Center. Shapley additive explanation algorithms for feature importance ranking and pairwise correlation analysis were used to identify predictors of disease progression. Four primary disease progression clusters (slow, moderate and rapid converters or non-converters) were subdivided into groups by race and sex, yielding 16 sub-clusters of participants with distinct progression patterns. A multi-head and early-fusion convolutional neural network achieved the most competitive performance and demonstrated superiority over a single-head deep learning architecture and conventional tree-based machine-learning methods, with 97% test accuracy, 96% F1 score and 0.19 root mean square error. From 447 features, 2 sets of 100 predictors of disease progression were extracted. Feature importance ranking, correlation analysis and descriptive statistics further enriched cluster analysis and validation of the heterogeneity of risk factors.

The weighted GS-PIA algorithm for cubic B-spline curve interpolations and convergence analysis

The weighted GS-PIA algorithm for cubic B-spline curve interpolations and convergence analysis

Large DNA deletions occur during DNA repair at 20-fold lower frequency for base editors and prime editors than for Cas9 nucleases.

When used to edit genomes, Cas9 nucleases produce targeted double-strand breaks in DNA. Subsequent DNA-repair pathways can induce large genomic deletions (larger than 100 bp), which constrains the applicability of genome editing. Here we show that Cas9-mediated double-strand breaks induce large deletions at varying frequencies in cancer cell lines, human embryonic stem cells and human primary T cells, and that most deletions are produced by two repair pathways: end resection and DNA-polymerase theta-mediated end joining. These findings required the optimization of long-range amplicon sequencing, the development of a k-mer alignment algorithm for the simultaneous analysis of large DNA deletions and small DNA alterations, and the use of CRISPR-interference screening. Despite leveraging mutated Cas9 nickases that produce single-strand breaks, base editors and prime editors also generated large deletions, yet at approximately 20-fold lower frequency than Cas9. We provide strategies for the mitigation of such deletions.

Volumetric Integrated Classification Index: An Integrated Voxel-Based Morphometry and Machine Learning Interpretable Biomarker for Post-Traumatic Stress Disorder.

PTSD is a complex mental health condition triggered by individuals' traumatic experiences, with long-term and broad impacts on sufferers' psychological health and quality of life. Despite decades of research providing partial understanding of the pathobiological aspects of PTSD, precise neurobiological markers and imaging indicators remain challenging to pinpoint. This study employed VBM analysis and machine learning algorithms to investigate structural brain changes in PTSD patients. Data were sourced ADNI-DoD database for PTSD cases and from the ADNI database for healthy controls. Various machine learning models, including SVM, RF, and LR, were utilized for classification. Additionally, the VICI was proposed to enhance model interpretability, incorporating SHAP analysis. The association between PTSD risk genes and VICI values was also explored through gene expression data analysis. Among the tested machine learning algorithms, RF emerged as the top performer, achieving high accuracy in classifying PTSD patients. Structural brain abnormalities in PTSD patients were predominantly observed in prefrontal areas compared to healthy controls. The proposed VICI demonstrated classification efficacy comparable to the optimized RF model, indicating its potential as a simplified diagnostic tool. Analysis of gene expression data revealed significant associations between PTSD risk genes and VICI values, implicating synaptic integrity and neural development regulation. This study reveals neuroimaging and genetic characteristics of PTSD, highlighting the potential of VBM analysis and machine learning models in diagnosis and prognosis. The VICI offers a promising approach to enhance model interpretability and guide clinical decision-making. These findings contribute to a better understanding of the pathophysiological mechanisms of PTSD and provide new avenues for future diagnosis and treatment.

Prognostic value of EMT-related genes and immune cell infiltration in thyroid carcinoma

BackgroundThe Epithelial–Mesenchymal Transition (EMT) is a very important process involved in cancer invasion and metastasis. Additionally, the Cathepsin K (CTSK) gene is closely related to the degradation of the extracellular matrix, which is a critical component of the EMT. The purpose of this study was to determine the relationships between EMT-related genes and immune cell infiltration and their prognostic value in Thyroid carcinoma (THCA). The effect of the CTSK gene on the aggressive biological features of THCA was assessed.MethodsWithin the framework of the present study, the THCA cohort was analyzed in detail based on data obtained from The TCGA database in the context of the EMT. The TCGA-THCA cohort was then divided into two groups, namely, high- and low-risk groups, based on the calculated EMT scores. Finally, based on the findings from the Weighted Gene Co-Expression Network Analysis (WGCNA) algorithm, LASSO regression analysis, and Kaplan−Meier plotter, we selected five genes (CTSK, C3ORF80, FBLN2, PRELP and SRPX2) associated with patient prognosis. Furthermore, this study examined the presence of various immune cells within the THCA samples using three distinct algorithms, namely ssGSEA, xCell, and MCPcounter. Additional studies have been conducted to establish the roles of CTSK in THCA cell proliferation and migration using various assays, such as CCK8, colony formation, EdU proliferation, Transwell migration and wound healing assays. Additionally, the involvement of CTSK in the regulation of various EMT-related markers was confirmed using Western blot analysis.ResultsBased on EMT scores, TCGA-THCA patients were further divided into two groups, and the study revealed that patients in the high-risk group had a worse prognosis than those in the low-risk group. Among the five genes linked to the prognostic value of EMT (CTSK, C3ORF80, FBLN2, PRELP, and SRPX2), CTSK exhibited notably elevated expression in the high-risk cohort. This group also exhibited pronounced immune cell infiltration, with a marked correlation observed between CTSK expression and the levels of macrophages, MDSCs, and various T-cell subtypes. Furthermore, in vitro studies demonstrated that reducing CTSK expression led to significant reductions in THCA cell viability; clonogenic, proliferative, motility and migratory capacities; and the expression of key EMT-related proteins, including N-cadherin, vimentin, slug, and snail.ConclusionOur results suggest that the expression of CTSK, a gene associated with the EMT, may be associated with THCA onset and progression and thus may serve as a promising prognostic biomarker.

The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms

Methods for early non-invasive diagnosis of melanoma using computer vision systems are considered. Existing computer vision systems using neural networks for classifying dermoscopic images do not allow tracking which diagnostic features are used to assign images to a particular class, reducing physicians' trust in the results. As an alternative, an image analysis algorithm is proposed with the ability to present justifications for decisions made at each processing stage. The implementation of this algorithm is based on the medical algorithm of modified globular pattern analysis. A significant sign of malignancy in a neoplasm is its asymmetry. This criterion is widely used by doctors in visual assessment of skin neoplasms. However, currently, the issues of evaluating the symmetry of globular patterns in artificial intelligence systems are not fully studied and described. A method for evaluating the symmetry of globular patterns in artificial intelligence systems for diagnosing skin neoplasms has been developed. A dataset of dermoscopic images was formed, containing 50 images each of neoplasms with symmetrically and asymmetrically arranged globular patterns. Methods for isolating the neoplasm area and globules are described. A classification system based on a set of 12 quantitative symmetry characteristics has been developed. The Random Forest algorithm was used to classify images based on symmetry features. In the conducted experiment, a classification accuracy of 85% was achieved. The presented results contribute to the development of computer vision methods in dermatology and demonstrate the possibility of using the proposed method in clinical decision support systems for modified analysis of dermoscopic patterns for diagnosing skin neoplasms.

Comparison of the OpenPose system and the reference optoelectronic system for gait analysis of lower-limb angular parameters in children.

Quantitative Gait Analysis (QGA) is the gold-standard for detailed study of lower-limb movement, angles and forces, especially in pediatrics, providing a decision aid for treatment and for assessment of results. However, widespread use of QGA is hindered by the need for specific equipment and trained personnel and high costs. Recently, the OpenPose system used algorithms for 2D video movement analysis, to determine joint points and angles without any supplementary equipment or great expertise. The present study therefore aimed to validate application of OpenPose for gait analysis in children with locomotor pathology, thereby circumventing the limitations of QGA. The OpenPose system is as precise as QGA for measuring lower-limb angles in gait in children. Gait analysis was studied prospectively, between January and July 2023, in 20 children: 13 boys, 7 girls; mean age, 13 years. There was no selection for pathology or use of walking aids. QGA was performed, measuring joint angles in the hips, knees and ankles. The same measurements were then made using the points obtained on OpenPose. The Mann-Whitney test was used to compare the two methods. There were only slight differences in angle measurements (in degrees) for the knees: right, 0.54 [-0.61 ; 1.71], p = 0.361; left, -1.09 [-2.16 ; 0.01], p = 0.051. Differences were greater for the hips (right, 9.32 [8.28 ; 10.35]; left, 7.54 [6.55 ; 8.54], p < 0.01) and ankles (right, -6.67 [-7.22 ; -6.12]; left, -7.07 [-7.60 ; -6.54], p < 0.01). OpenPose provided angle values close to those of QGA for the knees in the sagittal plane, independently of pathology and walking aid. In the hips and ankles, on the other hand, differences were too great to allow clinical application of OpenPose. IV.

Electric Vehicle Sentiment Analysis Using Large Language Models

Sentiment analysis is a technique used to understand the public’s opinion towards an event, product, or organization. For example, sentiment analysis can be used to understand positive or negative opinions or attitudes towards electric vehicle (EV) brands. This provides companies with valuable insight into the public’s opinion of their products and brands. In the field of natural language processing (NLP), transformer models have shown great performance compared to traditional machine learning algorithms. However, these models have not been explored extensively in the EV domain. EV companies are becoming significant competitors in the automotive industry and are projected to cover up to 30% of the United States light vehicle market by 2030 In this study, we present a comparative study of large language models (LLMs) including bidirectional encoder representations from transformers (BERT), robustly optimised BERT (RoBERTa), and a generalised autoregressive pre-training method (XLNet) using Lucid Motors and Tesla Motors YouTube datasets. Results evidenced that LLMs like BERT and her variants are off-the-shelf algorithms for sentiment analysis, specifically when fine-tuned. Furthermore, our findings present the need for domain adaptation whilst utilizing LLMs. Finally, the experimental results showed that RoBERTa achieved consistent performance across the EV datasets with an F1 score of at least 92%.

Genetic barcodes for species identification and phylogenetic estimation in ghost spiders (Araneae: Anyphaenidae: Amaurobioidinae).

The identification of spider species presents many challenges, since in most cases the characters used are from genital structures that are only fully developed in the adult stage, hence the identification of immatures is most often not possible. Additionally, these structures usually also present some intra-specific variability, which in some cases makes the identification of closely related species difficult. The genetic barcode technique (DNA barcodes), based on sequencing of the mitochondrial marker cytochrome c oxidase subunit I (COI ), has proven a useful, complementary tool to overcome these limitations. In this work, the contribution of DNA barcoding to the taxonomy of the subfamily Amaurobioidinae is explored using the refined single linkage analysis (RESL) algorithm for the delimitation of operational taxonomic units (OTUs), in comparison with the assemble species by automatic partitioning (ASAP) algorithm, and presented in conjunction with an updated molecular phylogenetic analysis of three other markers (28S rRNA, 16S rRNA, Histone H3 ), in addition to COI . Of a total of 97 included species identified by morphology, 82 species were concordant with the operational taxonomic units obtained from RESL, representing an 85% correspondence between the two methods. Similar results were obtained using the ASAP algorithm. Previous observations of morphological variation within the same species are supported, and this technique provides new information on genetic structure and potentially cryptic species. Most of the discrepancies between DNA barcoding and morphological identification are explained by low geographic sampling or by divergent or geographically structured lineages. After the addition of many specimens with only COI data, the multi-marker phylogenetic analysis is consistent with previous results and the support is improved. The markers COI , closely followed by 28S , are the most phylogenetically informative. We conclude that the barcode DNA technique is a valuable source of data for the delimitation of species of Amaurobioidinae, in conjunction with morphological and geographic data, and it is also useful for the detection of cases that require a more detailed and meticulous study.

Blood pressure abnormality detection and Interpretation utilizing Explainable Artificial Intelligence

ObjectiveHypertension is a pressing medical dysfunction that increases the risks of many fatal diseases. Early detection of hypertension can be crucial to lead a healthy life. Machine learning (ML) can be useful for the early prediction of a patient's likelihood of having a blood pressure abnormality and preventing it. Explainable artificial intelligence (XAI) is a state-of-the-art ML toolset that helps us understand and explain the prediction of an ML model. This research aims to build an automatic blood pressure anomaly detection system with maximum accuracy using the fewest features and learn why a model arrived at a particular result using XAI. MethodsThis research utilized the "Blood Pressure Data for Disease Prediction" dataset from Kaggle. Data were collected from medical reports of random participants in 2019 based on the presence of blood pressure abnormality, chronic kidney disease, and adrenal and thyroid disorders. We have used several ML algorithms (extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), decision tree (DT), and Logistic regression (LR)) to predict blood pressure abnormality based on patient's data. Principal component analysis (PCA) and recursive feature elimination (RFE) algorithms are used as feature optimizers. The receiver operating characteristic (ROC) curve analysis and accuracy were the key outcome metrics. Through the experiment, we have also calculated various performance measurement techniques like precision, recall, specificity, F1 score, and kappa to pin down the model with the best performance. Moreover, we have implemented several XAI methods namely permutation feature importance (PFI), partial dependence plots (PDP), Shapley additive explanations (SHAP), and local interpretable model-agnostic explanations (LIME) for additional exploration of our best model. ResultsThe combination of RFE and XGBoost provides the most significant results. The results of the study show that the algorithm has an AUC of 0.95, indicating good discriminatory power in detecting abnormal BP. The accuracy, precision, recall, specificity, F1-score, and kappa gained are 91.50%, 88.64%, 92.65%, 92.27%, 90.83%, and 0.8 respectively. According to the results of the XAI experiment, the genetic pedigree coefficient and hemoglobin level in a patient contribute the most to blood pressure abnormality prediction. Adrenal and thyroid diseases, as well as chronic kidney illness, have an impact on the projections. Existing research backs up this conclusion. ConclusionWhile comparing to previous works on this dataset, the results of our research are superior and the use of XAI shed new light on our model's prediction. This study would provide new insight into blood pressure detection in the medical profession.

Single-cell and machine learning approaches uncover intrinsic immune-evasion genes in the prognosis of hepatocellular carcinoma

Background and aimsHepatocellular carcinoma (HCC) is a tumor of high heterogeneity and complexity, which poses significant challenges to effective treatment and patient prognosis because of its immune evasion characteristics. To address these issues, single-cell technology and machine learning methods have emerged as a promising approach to identify genes associated with immune escape in HCC. This study aimed to develop a prognostic risk score model for HCC by identifying intrinsic immune-evasion genes (IIEGs) through single-cell technology and machine learning, providing insights into immune infiltration, enhancing predictive accuracy, and facilitating the development of more effective treatment strategies. Materials and methodsThe study utilized data from The Cancer Genome Atlas database to analyze gene expression profiles and clinical data related to intrinsic immune evasion in patients with HCC. Various tools, including the Human Protein Atlas, cBioPortal, single-cell analysis, machine learning, and Kaplan-Meier plot, were used to analyze IIEGs. Functional enrichment analysis was conducted to explore potential mechanisms. In addition, the abundance of infiltrating cells in the tumor microenvironment was investigated using single-sample gene set enrichment analysis, CIBERSORT, xCELL, and tumor immunophenotype algorithms. The expression of glycosylphosphatidylinositol anchor attachment 1 (GPAA1) was examined in the clinical sample of HCC by quantitative real-time polymerase chain reaction, Western blotting, and immunohistochemical staining. ResultsUnivariate Cox analysis identified 63 IIEGs associated with the prognosis of HCC. Using random forest, least absolute shrinkage and selection operator regression analysis, and support vector machine, a risk score model consisting of six IIEGs (carbamoyl-phosphate synthetase 2, aspartate transcarbamylase, and dihydroorotase (CAD), phosphatidylinositol glycan anchor biosynthesis class U (PIGU), endoplasmic reticulum membrane protein complex subunit 3 (EMC3), centrosomal protein 55 (CEP55), autophagy-related 10 (ATG10), and GPAA1) developed, which was validated using 10 pairs of HCC and adjacent non-cancerous samples. Based on the calculated median risk score, HCC samples were categorized into high- and low-risk groups. The Kaplan-Meier curve analysis showed that the high-risk group had a worse prognosis compared with the low-risk group. Time-dependent receiver operating characteristic analysis demonstrated the accurate predictive capability of the risk score model for HCC prognosis. Furthermore, immune infiltration analysis showed a positive correlation between the risk score model and 40 immune checkpoint genes as well as Th2 cells. ConclusionsA prognostic risk score model was formulated by six IIEG signatures and showed promise in predicting the prognosis of patients diagnosed with HCC. The utilization of the IIEG risk score as a novel prognostic index, together with its significance as a valuable biomarker for immunotherapy in HCC, provides benefit for patients with HCC in determining therapeutic strategies for clinical application.

GALADRIEL: A facility for advancing engineering science relevant to rep-rated high energy density physics and inertial fusion energy experiments.

Many current and upcoming laser facilities used to study high-energy-density (HED) physics and inertial fusion energy (IFE) support operating at high rep-rates (HRRs) of ∼0.1-10Hz, yet many diagnostics, target-fielding strategies, and data storage methods cannot support this pace of operation. Therefore, established experimental paradigms must change for the community to progress toward rep-rated operation. To this end, we introduce the General Atomics LAboratory for Developing Rep-rated Instrumentation and Experiments with Lasers, or GALADRIEL, to serve as a test bed for developing and benchmarking the engineering science advancements required for HRR experiments. GALADRIEL was constructed from the ground up around a commercial 1TW (∼25 mJ in ∼25fs at 800nm) laser with diverse experimental applications in mind. Assembly of the basic framework of GALADRIEL concluded with commissioning shots generating ∼1-4MeV electrons via laser-wakefield acceleration (LWFA) using a nitrogen gas jet. Subsequent LWFA experiments operated at 1Hz, utilized instrument feedback for optimization, and stored all data in a custom-built NoSQL database system. From this database called MORIA, or the MOngodb Repository for Information Archiving, data are retrievable via individual files or en masse by query requests defined by the user. GALADRIEL focuses on outstanding questions in engineering science, including targetry, diagnostics, data handling, environmental and materials studies, analysis and machine learning algorithm development, and feedback control systems. GALADRIEL fills a niche presently missing in the US-based user-facility community by providing a flexible experimental platform to address problems in engineering science relevant to rep-rated HED and IFE experiments.

Long-term, automated stool monitoring using a novel smart toilet: A feasibility study.

Patients' report of bowel movement consistency is unreliable. We demonstrate the feasibility of long-term automated stool image data collection using a novel Smart Toilet and evaluate a deterministic computer-vision analytic approach to assess stool form according to the Bristol Stool Form Scale (BSFS). Our smart toilet integrates a conventional toilet bowl with an engineered portal to image feces in a predetermined region of the plumbing post-flush. The smart toilet was installed in a workplace bathroom and used by six healthy volunteers. Images were annotated by three experts. A computer vision method based on deep learning segmentation and mathematically defined hand-crafted features was developed to quantify morphological attributes of stool from images. 474 bowel movements images were recorded in total from six subjects over a mean period of 10 months. 3% of images were rated abnormal with stool consistency BSFS 2 and 4% were BSFS 6. Our image analysis algorithm leverages interpretable morphological features and achieves classification of abnormal stool form with 94% accuracy, 81% sensitivity and 95% specificity. Our study supports the feasibility and accuracy of long-term, non-invasive automated stool form monitoring with the novel smart toilet system which can eliminate the patient burden of tracking bowel forms.

Identification of oxidative stress-related hub genes for predicting prognosis in diffuse large B-cell lymphoma

BackgroundOxidative stress is a cellular characteristic that might induce the proliferation and differentiation of tumor cells and promote tumor progression in diffuse large B-cell lymphoma (DLBCL). MethodsThe DLBCL gene sequencing dataset, tumor mutation burden data, copy number variation data of Somatic cell mutation data in TCGA were downloaded for data training analysis, along with four DLBCL datasets in GEO for validation analysis. The known oxidative stress related genes (OSRGs) were collected from websites. The weighted gene co-expression network analysis (WGCNA) was conducted on the TCGA DLBCL dataset to obtain gene modules related to oxidative stress and intersected with the known OSRGs to obtain the hub genes, which were used to perform consensus clustering on the samples to obtain new phenotypes. Next, the prognosis related OSRGs were selected through regression analysis algorithms and key genes were identified. These genes were used to establish the prognostic risk model and predictive model, and to compare functional and pathway differences among different risk groups. ResultsThrough website search, we obtained 297 known OSRGs, and after intersecting with WGCNA results, we obtained 26 OSRGs. The TCGA-DLBC samples were clustered into 2 subtypes with these genes and there were significant differences in immune infiltration between subtypes. After regression analysis, we obtained a total of four key genes, BMI1, CDKN1A, NOX1, and SESN1. The risk prediction model established with these four genes as variables has accurate prognostic prediction ability. The key genes interact with 65 miRNAs, 57 TFs, 47 RBPs, and 62 drugs, respectively, and are closely related to immune infiltration of the disease. Among them, CDKN1A and SESN1 had the highest variability. ConclusionsThe key genes involved in oxidative stress could predict the prognosis of DLBCL and potentially become therapeutic targets.

On-the-fly clustering for exascale molecular dynamics simulations

Computational resources have experienced exponential growth in the last decades enabling the simulation of complex physical problems at the cost of a massive increase in data storage. This is especially true for N-body simulations now reaching billions or trillions particles in certain cases. To overcome the drawbacks of data storage on disk for post-processing purposes, on-the-fly analysis has gained momentum but still represents a challenge in both its implementation and efficiency without impacting the simulation engine performances. This work provides a new in-situ procedure for features detection in massive N-body simulations, leveraging state-of-the-art techniques from various fields. Based on a discrete-to-continuum paradigm shift, particles and their respective physical quantities are projected onto a 3D regular grid before applying image analysis algorithms to group voxels based on specific user-defined criteria. A significant extension to the hybrid parallelism of connected component analysis within the image processing community is also introduced in the present study. Traditionally operating in shared memory parallelism, this extension now incorporates both distributed and shared memory approaches. The implementation is carried out within the exaStamp classical Molecular Dynamics code, a variant of the open-source exaNBody platform (see section 6). This adaptation allows for the on-the-fly analysis of multi-billion atoms samples with at most a 1.3% overhead. In addition, the entire framework is benchmarked up to 32768 cores. The applicability of the present approach is demonstrated on the case of a spall fracture in a tantalum sample as well as high velocity impact of a tin droplets on a rigid surface.

An Empirical Algorithm for Estimating the Absorption of Colored Dissolved Organic Matter from Sentinel-2 (MSI) and Landsat-8 (OLI) Observations of Coastal Waters

Sentinel-2/MSI and Landsat-8/OLI sensors enable the mapping of ocean color-related bio-optical parameters of surface coastal and inland waters. While many algorithms have been developed to estimate the Chlorophyll-a concentration, Chl-a, and the suspended particulate matter, SPM, from OLI and MSI data, the absorption by colored dissolved organic matter, acdom, a key parameter to monitor the concentration of dissolved organic matter, has received less attention. Herein we present an inverse model (hereafter referred to as AquaCDOM) for estimating acdom at the wavelength 412 nm (acdom (412)), within the surface layer of coastal waters, from measurements of ocean remote sensing reflectance, Rrs (λ), for these two high spatial resolution (around 20 m) sensors. Combined with a water class-based approach, several empirical algorithms were tested on a mixed dataset of synthetic and in situ data collected from global coastal waters. The selection of the final algorithms was performed with an independent validation dataset, using in situ, synthetic, and satellite Rrs (λ) measurements, but also by testing their respective sensitivity to typical noise introduced by atmospheric correction algorithms. It was found that the proposed algorithms could estimate acdom (412) with a median absolute percentage difference of ~30% and a median bias of 0.002 m−1 from the in situ and synthetic datasets. While similar performances have been shown with two other algorithms based on different methodological developments, we have shown that AquaCDOM is much less sensitive to atmospheric correction uncertainties, mainly due to the use of band ratios in its formulation. After the application of the top-of-atmosphere gains and of the same atmospheric correction algorithm, excellent agreement has been found between the OLI- and MSI-derived acdom (412) values for various coastal areas, enabling the application of these algorithms for time series analysis. An example application of our algorithms for the time series analysis of acdom (412) is provided for a coastal transect in the south of Vietnam.

Spectral and temporal acoustic differences between English and Dutch vowels

This study aims to compare the acoustic characteristics of English and Dutch vowels and to model the perception of Dutch vowels by English speakers on the basis of crosslinguistic acoustic similarity. The first three formant frequencies and the duration of vowels were extracted from the output of 20 native English and 20 native Dutch speakers. A linear discriminant analysis (LDA) algorithm was trained on the productions of English speakers and the Dutch productions were later supplied to the model to provide a predicted proportion of how each nonnative vowel would be classified in terms of the speakers’ L1 categories. The results of LDA demonstrated that all but one Dutch vowel were classified as above-chance responses in terms of two or more English categories. Due to the large and complex vowel system of English, completely overlapping contrasts were absent, while there was a large number of partially overlapping contrasts, which are predicted to exhibit moderate-to-good discrimination. The results of crosslinguistic acoustic similarity are largely consistent with those involving other English listeners of Dutch, potentially highlighting the importance of acoustic cues in estimating listeners’ speech perception patterns.

The development of a method for increasing the reliability of the assessment of the state of the object

The object of the research is assessment of object with different degrees of embeddedness. The subject of the research is the process of assessing the state of objects using the apparatus of neuro-fuzzy expert systems, the apparatus of relational analysis and bio-inspired algorithms. The problem that is solved in the research is to increase the reliability of the assessment of the objects state, regardless of the number of attachments. The originality of the research is that: – possibility of increasing the reliability of the object state assessment due to the parallel use of two bio-inspired algorithms; – taking into account the degree of awareness of the object state, due to the application of correction coefficients for the degree of awareness; – construction of both object and relational models, which allows to increase the reliability of assessment of the objects state; – possibility of combining the results of the work of bio-inspired algorithms, which makes it possible to mutually verify the correctness of the work of each of the algorithms; – universality of solving the task of assessing the state of objects with different degrees due to the hierarchical nature of their description; – possibility of simultaneously searching for a solution in different directions; – adequacy of the obtained results. An example of the use of the proposed method is presented on the example of solving the task of determining the composition of an operational group of troops (forces) and elements of its operational construction. The specified example showed an increase in the reliability of the assessment of the objects state by an average of 20 % due to the use of additional improved procedures. It is advisable to use the proposed method to solve the problems of assessing the state of multidimensional objects in conditions of uncertainty and risks, which are characterized by high requirements for the reliability of the information obtained

Non-destructive and rapid identification of yeasts by nearinfrared spectroscopy and machine learning

This study aimed to apply near-infrared (NIR) spectroscopy combined with machine learning techniques to identify yeast strains rapidly and practically, comparing the results with traditional molecular identification methods. Yeasts were isolated from the digestive tracts of aquatic mining insects collected in the extreme north of the Western Amazon (Roraima), Brazil, and preserved through cryopreservation and mineral oil methods. Molecular identification involved PCR amplification and sequencing of ribosomal DNA regions. NIR spectroscopy, coupled with multivariate analysis and machine learning algorithms such as principal component analysis (PCA), hierarchical cluster analysis (HCA), k-nearest neighbor (KNN), and soft independent modeling by class analogy (SIMCA), was used to analyze and classify the yeast samples, accurately identified yeast strains at the genus and species levels, achieving 100% accuracy in both the calibration and validation sets. The results indicate that this method provides a rapid, non-destructive, and environmentally friendly alternative to traditional molecular techniques, making it suitable for real-time, in situ analysis with minimal sample manipulation.

Multi-Search Strategy-based Improved Water Flow Optimizer Algorithm for Cluster Analysis

Clustering is a popular technique that has proven its capability in diverse fields like data analytics, business intelligence, social mining, image recognition, document clustering and bioinformatics. This technique determines the valuable information from a pre-defined set of data and groups similar information into the same cluster. In literature, many algorithms have been presented based on several clustering approaches. It is observed that partitional clustering algorithms are widely popular due to there simplicity and easy implementation such as k-means, k-medoids, and k-harmonic means. However, traditional algorithms suffer from several limitations like being trapped in local optima and depending on the initial solution quality. Heuristic algorithms are also proposed to alleviate the problems of traditional clustering algorithms. But, sometimes, these algorithms also get stuck in local minima and exhibit a lack of balance between search mechanisms. Hence, this work presents an improved water flow optimizer (IWFO) algorithm for cluster analysis that can address the issues of traditional and heuristic algorithms. In the proposed IWFO algorithm, the initial solution is generated based on the logistic chaotic map instead of random initialization, and in turn, an optimal quality solution is generated. The search mechanism of the WFO algorithm is enhanced based on an improved search mechanism which is the combination of non-linear functions and the previous best solution. Further, the local optima issue is alleviated using a multi-start search mechanism. The efficacy of the proposed IWFO algorithm is evaluated using twelve benchmark clustering datasets and results are compared with seventeen clustering algorithms. The simulation results are assessed using intra-cluster distance (intra), standard deviation (SD), rank, accuracy rate (AR) and detection rate (DR) parameters. Further, a statistical test is also conducted to validate the efficacy of the proposed IWFO algorithm. The results showed that proposed IWFO algorithms obtain superior quality results on most of the datasets.