Discriminant Analysis Algorithm Research Articles

Network intrusion detection in big datasets using Spark environment and incremental learning

<p class="Abstract">Internet of things (IoT) systems have experienced significant growth in data traffic, resulting in security and real-time processing issues. Intrusion detection systems (IDS) are currently an indispensable tool for self-protection against various attacks. However, IoT systems face serious challenges due to the functional diversity of attacks, resulting in detection methods with machine learning (ML) and limited static models generated by the linear discriminant analysis (LDA) algorithm. The process entails adjusting the model parameters in real time as new data arrives. This paper proposes a new method of an IDS based on the LDA algorithm with the incremental model. The model framework is trained and tested on the IoT intrusion dataset (UNSW-NB15) using the streaming linear discriminant analysis (SLDA) ML algorithm. Our approach increased model accuracy after each training, resulting in continuous model improvement. The comparison reveals that our dynamic model becomes more accurate after each batch and can detect new types of attacks.</p>

Predicting intraoperative 5-ALA-induced tumor fluorescence via MRI and deep learning in gliomas with radiographic lower-grade characteristics.

Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely sampled to avoid undergrading. We aimed to analyze whether a deep learning model could predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). We evaluated a cohort of 163 glioma patients categorized intraoperatively as fluorescent (n = 83) or non-fluorescent (n = 80). The preoperative MR images of gliomas lacking high-grade characteristics (e.g., necrosis or irregular ring contrast-enhancement) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a tenfold cross-validation procedure. Our proposed approach's performance was assessed using mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. Our findings highlight the potential of a U-Net model, coupled with a Random Forest classifier, for pre-operative prediction of intraoperative fluorescence. We achieved high accuracy using the features extracted by the U-Net model pre-trained for brain tumor segmentation. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.

Machine Learning Approaches for the Fusion of Near-Infrared, Mid-Infrared, and Raman Data to Identify Cartilage Degradation in Human Osteochondral Plugs.

Vibrational spectroscopy methods such as mid-infrared (MIR), near-infrared (NIR), and Raman spectroscopies have been shown to have great potential for in vivo biomedical applications, such as arthroscopic evaluation of joint injuries and degeneration. Considering that these techniques provide complementary chemical information, in this study, we hypothesized that combining the MIR, NIR, and Raman data from human osteochondral samples can improve the detection of cartilage degradation. This study evaluated 272 osteochondral samples from 18 human knee joins, comprising both healthy and damaged tissue according to the reference Osteoarthritis Research Society International grading system. We established the one-block and multi-block classification models using partial least squares discriminant analysis (PLSDA), random forest, and support vector machine (SVM) algorithms. Feature modeling by principal component analysis was tested for the SVM (PCA-SVM) models. The best one-block models were built using MIR and Raman data, discriminating healthy cartilage from damaged with an accuracy of 77.5% for MIR and 77.8% for Raman using the PCA-SVM algorithm, whereas the NIR data did not perform as well achieving only 68.5% accuracy for the best model using PCA-SVM. The multi-block approach allowed an improvement with an accuracy of 81.4% for the best model by PCA-SVM. Fusing three blocks using MIR, NIR, and Raman by multi-block PLSDA significantly improved the performance of the single-block models to 79.1% correct classification. The significance was proven by statistical testing using analysis of variance. Thus, the study suggests the potential and the complementary value of the fusion of different spectroscopic techniques and provides valuable data analysis tools for the diagnostics of cartilage health.

Development of a novel sustainable, portable, fast, and non-invasive platform based on ATR-FTIR technology coupled with machine learning algorithms for Helicobacter pylori detection in human saliva

Helicobacter pylori (H. pylori) infection can increase the risk of peptic ulcers and gastric neoplasms. H. pylori detection in gastric epithelial tissue collected by esophagogastroduodenoscopy (EGD) is an invasive, costly, and stands as an invasive and examiner-dependent procedure necessitating suitable sedation. complex execution procedure, reducing access for isolated populations. H. pylori detection by Urea Breath Test (UBT) presents high outlay cost with limited access in low- and middle-income countries. In this context, it is critical to develop novel alternative non-invasive platforms for the portable, fast, accessible through self-collection and reagent-free detection of H. pylori. Here, we used attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR) supported by Machine Learning algorithms to identify infrared vibrational modes of H. pylori diluted in human saliva. To perform it, saliva was diluted in 4 different concentrations (108 CFU/mL, 107 CFU/mL, 106 CFU/mL, and 105 CFU/mL) of H. pylori. Then, diluted saliva with or without H. pylori were applied to ATR-FTIR spectroscopy to perform a reagent-free, fast, and sustainable analysis of spectral signatures to identify unique vibrational modes to identify this pathogen. The obtained spectra were applied to Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) algorithms to perform the H. pylori detection. The results indicate that the method was highly accurate between 108 - 105 CFU/mL, achieving an accuracy of 89% for 108 CFU/mL, 93% for 107 CFU/mL, 94% for 106 CFU/mL, and 85% for 105 CFU/mL with SVM algorithm. This proof-of-concept study demonstrates the significant potential of a biophotonic platform supported by artificial intelligence for the non-invasive detection of H. pylori in human saliva samples obtained by self-collection, without the use of reagents. The data reveal that this proof-of-concept study has significant potential for the non-invasive detection of H. pylori using a biophotonic platform supported by artificial intelligence without the use of reagents with human saliva samples obtained by self-collection.

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.

New Quadratic Discriminant Analysis Algorithms for Correlated Audiometric Data.

Paired organs like eyes, ears, and lungs in humans exhibit similarities, and data from these organs often display remarkable correlations. Accounting for these correlations could enhance classification models used in predicting disease phenotypes. To our knowledge, there is limited, if any, literature addressing this topic, and existing methods do not exploit such correlations. For example, the conventional approach treats each ear as an independent observation when predicting audiometric phenotypes and is agnostic about the correlation of data from the two ears of the same person. This approach may lead to information loss and reduce the model performance. In response to this gap, particularly in the context of audiometric phenotype prediction, this paper proposes new quadratic discriminant analysis (QDA) algorithms that appropriately deal with the dependence between ears. We propose two-stage analysis strategies: (1) conducting data transformations to reduce data dimensionality before applying QDA; and (2) developing new QDA algorithms to partially utilize the dependence between phenotypes of two ears. We conducted simulation studies to compare different transformation methods and to assess the performance of different QDA algorithms. The empirical results suggested that the transformation may only be beneficial when the sample size is relatively small. Moreover, our proposed new QDA algorithms performed better than the conventional approach in both person-level and ear-level accuracy. As an illustration, we applied them to audiometric data from the Medical University of South Carolina Longitudinal Cohort Study of Age-related Hearing Loss. In addition, we developed an R package, PairQDA, to implement the proposed algorithms.

Decoding wheat contamination through self-assembled whole-cell biosensor combined with linear and non-linear machine learning algorithms

The contamination of mycotoxins is a serious problem around the world. It has detrimental effects on human beings and leads to tremendous economic loss. It is essential to develop a rapid and non-destructive method for contamination recognition particularly for early alarm. In this study, the whole-cell biosensor array was constructed and employed for rapid recognition of wheat contamination by combining with machine learning algorithms. Seven key VOCs were explored through univariate coupling to multivariate analysis of orthogonal partial least squares-discrimination analysis (OPLS-DA) models. The promoters of dnaK, katG, oxyR, soxS obtained from the stress-responsive of key VOCs were fused to the bacterial operon and fabricated on the whole-cell biosensor. The constructed whole-cell biosensor array was consisted with four kinds of sensors and 18 sensor unit. The bioluminescent intensity combined with linear machine learning algorithm of partial least squares discriminant analysis (PLS-DA) and non-linear algorithms of back propagating artificial neural network (BP-ANN) and least square support vector machine (LS-SVM) were employed to establish discrimination models for mold contamination especially for early warning. The Monte-Carlo strategy was performed to generate thirty subsets for modeling to give more reliable results. As a result, the whole-cell biosensor combined with non-linear algorithm of LS-SVM was practicable for detecting mold identification for wheat early-warning with the accuracy of 97.24%. Additionally, this study provides practical and effective methods not only for wheat quality guarantee and supervision but also for other foodstuffs.

P10.22.B PREDICTING INTRAOPERATIVE 5-ALA-INDUCED TUMOR FLUORESCENCE VIA MRI AND DEEP LEARNING IN GLIOMAS WITH RADIOGRAPHIC LOWER-GRADE CHARACTERISTICS

Abstract BACKGROUND Lower-grade gliomas typically exhibit 5-aminolevulinic acid (5-ALA)-induced fluorescence in only 20-30% of cases, a rate that can be increased by doubling the administered dose of 5-ALA. Fluorescence can depict anaplastic foci, which can be precisely resected to avoid undergrading. We aimed to analyze whether a deep learning model can predict intraoperative fluorescence based on preoperative magnetic resonance imaging (MRI). Material and Methods: The MRI images of gliomas lacking high-grade characteristics (necrosis, extended contrast-enhancement, a.o.) consisted of T1, T1-post gadolinium, and FLAIR sequences. The preprocessed MRIs were fed into an encoder-decoder convolutional neural network (U-Net), pre-trained for tumor segmentation using those three MRI sequences. We used the outputs of the bottleneck layer of the U-Net in the Variational Autoencoder (VAE) as features for classification. We identified and utilized the most effective features in a Random Forest classifier using the principal component analysis (PCA) and the partial least square discriminant analysis (PLS-DA) algorithms. We evaluated the performance of the classifier using a 10-fold cross-validation procedure. RESULTS We evaluated a cohort of 163 glioma patients categorized as fluorescent (n=83) or non-fluorescent (n=80). Our proposed approach’s performance was evaluated using metrics such as mean balanced accuracy, mean sensitivity, and mean specificity. The optimal results were obtained by employing top-performing features selected by PCA, resulting in a mean balanced accuracy of 80% and mean sensitivity and specificity of 84% and 76%, respectively. CONCLUSION Our findings highlight the potential of a U-Net model, coupled with a random forest classifier, for intraoperative fluorescence prediction. We achieved good accuracy using advanced techniques such as deep learning-based tumor segmentation and Variational Autoencoder for radiomics feature extraction. While the model can still be improved, it has the potential for evaluating when to administer 5-ALA to gliomas lacking typical high-grade radiographic features.

High accuracy model for HBsAg loss based on longitudinal trajectories of serum qHBsAg throughout long-term antiviral therapy

ObjectiveHepatitis B surface antigen (HBsAg) loss is the optimal outcome for patients with chronic hepatitis B (CHB) but this rarely occurs with currently approved therapies. We aimed to develop and...

Noninvasive brain stimulation during EEG improves machine learning classification in chronic stroke.

In individuals with chronic stroke and hemiparesis, noninvasive brain stimulation (NIBS) may be used as an adjunct to therapy for improving motor recovery. Specific states of movement during motor recovery are more responsive to brain stimulation than others, thus a system that could auto-detect movement state would be useful in correctly identifying the most effective stimulation periods. The aim of this study was to compare the performance of different machine learning models in classifying movement periods during EEG recordings of hemiparetic individuals receiving noninvasive brain stimulation. We hypothesized that transcranial direct current stimulation, a form of NIBS, would modulate brain recordings correlating with movement state and improve classification accuracies above those receiving sham stimulation. Electroencephalogram data were obtained from 10 participants with chronic stroke and 11 healthy individuals performing a motor task while undergoing transcranial direct current stimulation. Eight traditional machine learning algorithms and five ensemble methods were used to classify two movement states (a hold posture and an arm reaching movement) before, during and after stimulation. To minimize compute times, preprocessing and feature extraction were limited to z-score normalization and power binning into five frequency bands (delta through gamma). Classification of disease state produced significantly higher accuracies in the stimulation (versus sham) group at 78.9% (versus 55.6%, p < 0.000002). We observed significantly higher accuracies when classifying stimulation state in the chronic stroke group (77.6%) relative to healthy controls (64.1%, p < 0.0095). In the chronic stroke cohort, classification of hold versus reach was highest during the stimulation period (75.2%) as opposed to the pre- and post-stimulation periods. Linear discriminant analysis, logistic regression, and decision tree algorithms classified movement state most accurately in participants with chronic stroke during the stimulation period (76.1%). For the ensemble methods, the highest classification accuracy for hold versus reach was achieved using low gamma frequency (30-50 Hz) as a feature (74.5%), although this result did not achieve statistical significance. Machine learning algorithms demonstrated sufficiently high movement state classification accuracy in participants with chronic stroke performing functional tasks during noninvasive brain stimulation. tDCS improved disease state and movement state classification in participants with chronic stroke.

Research on Silage Corn Forage Quality Grading Based on Hyperspectroscopy

Corn silage is the main feed in the diet of dairy cows and other ruminant livestock. Silage corn feed is very susceptible to spoilage and corruption due to the influence of aerobic secondary fermentation during the silage process. At present, silage quality testing of corn feed mainly relies on the combination of sensory evaluation and laboratory measurement. The sensory review method is difficult to achieve precision and objectivity, while the laboratory determination method has problems such as cumbersome testing procedures, time-consuming, high cost, and damage to samples. In this study, the external sensory quality grading model for different qualities of silage corn feed was established using hyperspectral data. To explore the feasibility of using hyperspectral data for external sensory quality grading of corn silage, a hyperspectral system was used to collect spectral data of 200 corn silage samples in the 380–1004 nm band, and the samples were classified into four grades: excellent, fair, medium, and spoiled according to the German Agricultural Association (DLG) standard for sensory evaluation of silage samples. Three algorithms were used to preprocess the fodder hyperspectral data, including multiplicative scatter correction (MSC), standard normal variate (SNV), and S–G convolutional smoothing. To reduce the redundancy of the spectral data, variable combination population analysis (VCPA) and competitive adaptive reweighted sampling (CARS) were used for feature wavelength selection, and linear discriminant analysis (LDA) algorithm was used for data dimensionality reduction, constructing random forest classification (RFC), convolutional neural networks (CNN) and support vector machines (SVM) models. The best classification model was derived based on the comparison of the model results. The results show that SNV-LDA-SVM is the optimal algorithm combination, where the accuracy of the calibration set is 99.375% and the accuracy of the prediction set is 100%. In summary, combined with hyperspectral technology, the constructed model can realize the accurate discrimination of the external sensory quality of silage corn feed, which provides a reliable and effective new non-destructive testing method for silage corn feed quality detection.

Rapid prediction and visualization of safe moisture content in alfalfa seeds based on multispectral imaging technology

Moisture significantly impacts seed sales, storage, and processing. Traditional moisture testing methods are often slow, labor-intensive, and inadequate for the rapid detection demands of modern agriculture, particularly for non-destructive testing of individual seeds. This study applied multispectral imaging to obtain morphological and spectral data from alfalfa seeds at six moisture levels (4 %, 8 %, 12 %, 16 %, 25 %, and 41 %). By integrating algorithms such as Support Vector Machines (SVM), Random Forests (RF), Linear Discriminant Analysis (LDA), Back Propagation Neural Network (BPNN), and normalized typical discriminant analysis (nCDA) algorithms, classification models were developed to distinguish between safe and unsafe moisture levels. The Results indicated that spectral data alone significantly improved model accuracy and prediction. nCDA visualizations effectively illustrated spatial moisture distribution, highlighting stark color differences between seeds in the safe moisture range (4 %, 8 %, 12 %) and those in the unsafe range (16 %, 25 %, 41 %). BPNN exhibited high model precision, achieving a recognition accuracy rate of 90.1 % for safe and unsafe moisture content. Key wavelengths identified by the Permutation method included 970, 880, 570, and 490 nm. Pearson correlation analysis showed a significant positive correlation between germination indicators and spectral data, which strengthened with longer seed storage. These findings confirm the potential of multispectral imaging for assessing the safe moisture content of alfalfa seeds, supporting the development of detection systems for evaluating moisture content in individual seeds. This advancement enables the rapid removal of high-moisture seeds, preventing deterioration during storage.

F-Norm-Based Soft LDA Algorithm for Fault Detection in Chemical Production Processes.

In chemical production processes, outliers are inevitable. Many existing feature extraction algorithms are overly sensitive to outliers and excessively focus on secondary features while ignoring the key features in the data. To address this problem, the Frobenius norm based soft linear discriminant analysis algorithm (FBSLA) is proposed in this paper. Specifically, FBSLA uses the Frobenius norm instead of its square as a metric to enhance the robustness of the algorithm. Furthermore, a nonreduced dimensionality projection matrix is introduced to make the training data features more obvious. Additionally, soft constraint is adopted instead of the traditional hard constraint to reduce the sensitivity caused by outliers. To validate the effectiveness of FBSLA, in this paper, experiments are conducted on the Tennessee Eastman Process and the Penicillin Fermentation Process data sets. According to experimental results, FBSLA significantly outperforms other state-of-the-art algorithms in terms of fault detection accuracy.

THE DISCRIMINANT ANALYSIS FUNCTION WAS IMPLEMENTED TO PREDICT THE PRESENCE OF DIABETES

Diabetes is a condition blood sugar concentrations are high and there is something wrong with insulin inside the body. A hormone called insulin controls the equilibrium of blood sugar concentration in humans. Diabetes has high-risk health, such as CKD, CVD, skin disease or even blindness. The reason people suffer from diabetes is caused of bad consumption habits. Some symptoms of diabetes are frequent urination and feeling hungry too quickly. Diabetes is sometimes difficult to diagnose, which is why it is also referred to as the silent killer. A preventive way is an early prediction of diabetes disease. This is very important to do. In this study, the discriminant analysis algorithm is used along with machine learning techniques. In this study, machine learning techniques are used. Its name is discriminant analysis algorithm. Two popular versions are linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA). This method is used because it is suitable for high-dimensional data and the discriminant analysis algorithm has minimal parameters. The discriminant analysis algorithm uses few parameters and this method appropriate for high-dimensional data. We'll compare the two approaches to find a way to demonstrate their dependability. Both approaches would be contrasted. Based on the result, QDA has the best performance. QDA can produce accuracy = 93.7%, TPR = 93.7%, precision = 94.3%, recall = 93.7% and F-measure = 93.9%. FPR of QDA is the lowest one, it is 1.02%. It means QDA has a small error in making predictions. Overall, based on the result QDA is the proven and proper method for detecting diabetes disease

High accuracy discriminant analysis of preparation from 22 commercial antibodies based on UV spectroscopy combined with chemometrics

The demand for monoclonal antibodies (mAbs) in hospitals is continually rising due to the advancement of targeted therapy or immunotherapy. Typically, mAbs are produced in centralized chemotherapy production units and require rigorous control to ensure the right drug at the right dose before administration to patients.This study aimed to develop a robust discriminant analysis method using a large dataset comprising 22 mAbs used in cancer therapy. The discriminant analysis was based on UV spectroscopy coupled with chemometrics. A dataset consisting of 404 samples was prepared and analyzed using various preprocessing methods, wavelength selection and discriminant analysis algorithms to maximize overall accuracy. Validation of the newly developed discriminant analysis was conducted using samples collected from real manufactured preparations for patient (over 1,380 samples). The study achieved an overall accuracy of 99.6% and 99.8% on the 22 mAbs using partial least squares-discriminant analysis (PLS-DA) and k-nearest neighbors (kNN), respectively. The utilization of chemometrics for discriminating mAbs based on their UV spectra, following total area normalization, has been successfully demonstrated. This method has undergone validation, affirming its capability to swiftly and dependably distinguish different mAbs. Moreover, it effortlessly integrates within the workflow involved in the preparation of mAbs drugs within a cancer hospital setting. This advancement holds promise for streamlining processes and enhancing efficiency in the production and use of mAbs, thereby potentially benefiting patient care and treatment outcomes.

A Comprehensive Review on Discriminant Analysis for Addressing Challenges of Class-Level Limitations, Small Sample Size, and Robustness

The classical linear discriminant analysis (LDA) algorithm has three primary drawbacks, i.e., small sample size problem, sensitivity to noise and outliers, and inability to deal with multi-modal-class data. This paper reviews LDA technology and its variants, covering the taxonomy and characteristics of these technologies and comparing their innovations and developments in addressing these three shortcomings. Additionally, we describe the application areas and emphasize the kernel extensions of these technologies to solve nonlinear problems. Most importantly, this paper presents perspectives on future research directions and potential research areas in this field.

Diagnosis and classification of kidney transplant rejection using machine learning-assisted surface-enhanced Raman spectroscopy using a single drop of serum

The quest to reduce kidney transplant rejection has emphasized the urgent requirement for the development of non-invasive, precise diagnostic technologies. These technologies aim to detect antibody-mediated rejection (ABMR) and T-cell-mediated rejection (TCMR), which are asymptomatic and pose a risk of potential kidney damage. The protocols for managing rejection caused by ABMR and TCMR differ, and diagnosis has traditionally relied on invasive biopsy procedures. Therefore, a convergence system using a nano-sensing chip, Raman spectroscopy, and AI technology was introduced to facilitate diagnosis using serum samples obtained from patients with no major abnormality, ABMR, and TCMR after kidney transplantation. Tissue biopsy and Banff score analysis were performed across the groups for validation, and 5 μL of serum obtained at the same time was added onto the Au–ZnO nanorod-based Surface-Enhanced Raman Scattering sensing chip to obtain Raman spectroscopy signals. The accuracy of machine learning algorithms for principal component-linear discriminant analysis and principal component-partial least squares discriminant analysis was 93.53% and 98.82%, respectively. The collagen (an indicative of kidney injury), creatinine, and amino acid-derived signals (markers of kidney function) contributed to this accuracy; however, the high accuracy was primarily due to the ability of the system to analyze a broad spectrum of various biomarkers.

A highly sensitive SERS substrate of porous membrane-Ag NPs for kidney cancer detection

BackgroundThe substrate employed in surface-enhanced Raman spectroscopy (SERS) constitutes an essential element in the cancer detection methodology. In this research, we introduce a three-dimensional (3D) structured SERS substrate that integrates a porous membrane with silver nanoparticles to enhance SERS spectral signals through the utilization of the aggregation effect of silver nanoparticles. This enhancement is crucial because accurate detection results strongly depend on the intensity of specific peaks in Raman spectroscopy. A highly sensitive SERS substrate can significantly improve the accuracy of detection results. ResultsWe collected 66 plasma samples from individuals with kidney cancer and control individuals, including both bladder cancer patients and healthy individuals. Then, we utilized substrates with and without porous membranes to acquire the SERS spectra of the samples, enabling us to evaluate the enhancement effect of our SERS substrate. The spectral analysis demonstrated enhanced peak intensities in the experimental group (with porous substrate) compared to the control group (without porous substrate). The uniformity and reproducibility of the SERS substrate are also significantly enhanced, which is very helpful for improving the accuracy of detection results. Additionally, the Principal Component Analysis-Linear Discriminant Analysis algorithm (PCA-LDA) was employed to classify the SERS spectra of both groups. In the experimental group, the classification accuracy was 98.5 % for kidney cancer, and 83.3 % for kidney and bladder cancer. Compared to the control group, it improved by 3 % and 12.6 % respectively. SignificantThis indicates that our 3D structured SERS substrate combined with multivariate statistical algorithms PCA-LDA can not only improve the accuracy of SERS detection technology in single cancer detection, but also has great potential in multiple cancer detection. This 3D structured SERS substrate is expected to become a new auxiliary means for cancer detection.

Bearing fault diagnosis of induction machines using VMD-DWT and composite multiscale weighted permutation entropy

PurposeBearings play a critical role in the reliable operation of induction machines, and their failure can lead to significant operational challenges and downtime. Detecting and diagnosing these defects is imperative to ensure the longevity of induction machines and preventing costly downtime. The purpose of this paper is to develop a novel approach for diagnosis of bearing faults in induction machine.Design/methodology/approachTo identify the different fault states of the bearing with accurately and efficiently in this paper, the original bearing vibration signal is first decomposed into several intrinsic mode functions (IMFs) using variational mode decomposition (VMD). The IMFs that contain more noise information are selected using the Pearson correlation coefficient. Subsequently, discrete wavelet transform (DWT) is used to filter the noisy IMFs. Second, the composite multiscale weighted permutation entropy (CMWPE) of each component is calculated to form the features vector. Finally, the features vector is reduced using the locality-sensitive discriminant analysis algorithm, to be fed into the support vector machine model for training and classification.FindingsThe obtained results showed the ability of the VMD_DWT algorithm to reduce the noise of raw vibration signals. It also demonstrated that the proposed method can effectively extract different fault features from vibration signals.Originality/valueThis study suggested a new VMD_DWT method to reduce the noise of the bearing vibration signal. The proposed approach for bearing fault diagnosis of induction machine based on VMD-DWT and CMWPE is highly effective. Its effectiveness has been verified using experimental data.

Rapid identification of pediatric brain tumors with differential mobility spectrometry.

Brain tumors are a major source of disease burden in pediatric population, with the most common tumor types being pilocytic astrocytoma, ependymoma and medulloblastoma. In every tumor entity, surgery is the cornerstone of treatment, but the importance of gross-total resection and the corresponding patient prognosis is highly variant. However, real-time identification of pediatric CNS malignancies based on the histology of the frozen sections alone is especially troublesome. We propose a novel method based on differential mobility spectrometry (DMS) analysis for rapid identification of pediatric brain tumors. We prospectively obtained tumor samples from 15 pediatric patients (5 pilocytic astrocytomas, 5 ependymomas and 5 medulloblastomas). The samples were cut into 36 smaller specimens that were analyzed with the DMS. With linear discriminant analysis algorithm, a classification accuracy (CA) of 70% was reached. Additionally, a 75% CA was achieved in a pooled analysis of medulloblastoma vs. gliomas. Our results show that the DMS is able to differentiate most common pediatric brain tumor samples, thus making it a promising additional instrument for real-time brain tumor diagnostics.