Excellent Classification Research Articles

Integrated Health Monitoring System using Fingerprint and Disease Risk Prediction

Recent developments in machine learning and biometric systems have had a big influence on healthcare applications. In order to provide a holistic approach to health monitoring, this research introduces a unique method that combines disease risk prediction with fingerprint-based blood group recognition. Based on user-provided health data, the system uses machine learning algorithms to determine the risk of common illnesses including diabetes, cardiovascular disease, and chronic kidney disease (CKD) and convolutional neural networks (CNNs) to identify blood type from fingerprint photos. Through the integration of fingerprint biometric data with health risk modelling, the suggested approach seeks to increase the precision and usability of health forecasts. The system's effectiveness is demonstrated by the evaluation's excellent classification accuracy for blood groups and trustworthy estimates of illness risk.This work demonstrates the possibility of integrating biometric data with predictive health models and offers a promising step toward customized healthcare solutions

ARLSSMM: an effective fault diagnosis method for roller bearing under strong noise

ABSTRACT Support matrix machine (SMM) is a matrix classification method that effectively utilises information between rows and columns in matrix-form data. However, the presence of abnormal data in the feature matrix fed into the model can result in model non-convergence and hyperplane shift, greatly affecting classification accuracy. To address this issue, this paper introduces a matrix classification method, called asymmetric robust least squares support matrix machine (ARLSSMM). To construct ARLSSMM, a novel optimisation model based on a matrix with asymmetric constraints is designed to obtain the hyperplane, which can not only use the data set to dynamically determine the position of the hyperplane to obtain the maximum margin space but also reduce the influence of abnormal data on the model classification performance. Two different roller bearing types of test data are used for experimental validation, and the results show that ARLSSMM demonstrates excellent classification performance.

A multi-scale modeling approach for predicting and mitigating thermal runaway in electric vehicle batteries

This study presents a unique multi-scale modelling technique for electric vehicle (EV) battery thermal runaway prediction models using electrochemical, thermal, and machine learning approaches. This modelling framework has illuminated the thermal runaway’s physical process and the race between heat production and dissipation at the cell module, and pack levels.Experimental evaluation has demonstrated solid predictive performance for each component. The modified pseudo-two-dimensional (P2D) electrochemical model has achieved high voltage prediction accuracy (mean absolute error: 8.5 mV), and the 3D thermal model has captured battery module temperatures with an average error of ± 1.5 °C.The machine learning model has exhibited 96.8% accuracy, excellent classification precision, and an 18.3-minute early warning time. It was also demonstrated that the integrated multi-scale model outperformed standalone single-scale models with 15% higher prediction accuracy and 32% higher average early warning time.Based on these findings, adaptive cooling techniques, unique charge/discharge procedures, and early isolation methods were created. Simulations showed that these mitigation techniques decreased thermal runaway occurrence by 78% and severity by 93%. Despite its high computing cost, this technique might improve EV battery safety, guide battery pack design, and accelerate EV adoption, which would cut carbon emissions.

Bearing fault diagnosis by sparse frequency spiral spectrum driven NAF-LDM under strong noise and small samples

Abstract The complexity of background noise and the scarcity of real fault samples seriously affect the diagnostic accuracy of the model. To address this, a noise-robust two-dimensional feature map, the sparse frequency spiral spectrum (SFSM), based on sparse representation theory, is proposed. A bridge penalty coefficient is applied to the sparse representation model to accurately select impact components, and the fast iterative shrinkage threshold algorithm is used to solve for sparse representation coefficients. Sparse reconstructed signals are obtained by convolving the impact patterns with these coefficients, leading to a sparse reconstruction algorithm with reduced computational complexity. Furthermore, the novel non-linear activation-free blocks (NAF Blocks) are embedded into the latent diffusion model to augment small samples, significantly improving image generation speed and quality. The integration of the Swin transformer for feature extraction and classification further enhances diagnostic performance. The superiority of this method is validated on the XJTU-SY dataset, a bearing experimental platform dataset, and enterprise engineering dataset. Experimental results demonstrate that the structural and generalization advantages of NAF Blocks are crucial for improving image quality and inference speed. The noise suppression capability of the proposed method, facilitated by the SFSM feature processing technique, is confirmed through ablation and noise robustness tests. Finally, the Swin transformer’s excellent feature extraction and classification capabilities for SFSM are verified. The proposed method achieves diagnostic accuracies of 99.10% and 98.7% on the XJTU-SY and experimental platform datasets, respectively.

Early plant disease detection by Raman spectroscopy: An open-source software designed for the automation of preprocessing and analysis of spectral dataset

This study introduces a reliable, non-coding software named qREAD-Raman, written in the JavaScript® language, for analyzing and interpreting Raman spectral information. It is designed with a focus on the early detection of diseases in tomato plants (S. lycopersicum) during the asymptomatic stage. The platform integrates a set of machine learning algorithms necessary for the preprocessing consisting of outlier removal, baseline correction, fluorescence removal, smoothing, and normalization. For classification, we applied a Consensus of five different classifiers: Multilayer Perceptron (MLP), Partial Least Squares-Discriminant Analysis (PLS-DA), Linear Discriminant Analysis (LDA), Long Short-Term Memory (LSTM), and K-nearest neighbors (kNN). The experiments were conducted on two bacterial diseases: bacterial canker of tomato induced by Clavibacter michiganesis subsp. michiganensis (Cmm), and the tomato vein-greening associated with Candidatus Liberibacter solanacearum (CLso), a non-culturable bacteria transmitted by Bactericera cockerelli insect. Binary models (Cmm-Healthy and CLso-Healthy) demonstrated excellent classification ability. Asymptomatic Cmm-infected plants were distinguished with an accuracy of 88–95 %, while CLso-infected plants showed an accuracy of 68–77 %. The three-class model (CLso-Cmm-Healthy) exhibited acceptable performance in differentiating between Cmm and CLso, with accuracy rates of 71–83% and 58–67%, respectively. The model's performance highlights differences in the relevant spectral regions associated with the biochemical changes induced by each studied disease. The qREAD-Raman software, implemented for the purpose of this research, was found to be a valuable and comprehensive tool that effectively differentiate diseased tomato plants during their asymptomatic stage.

Genetically-Encoded Fluorescence Barcodes for Single-Cell Analysis.

Genetically-encoded, single-cell barcodes are broadly useful for experimental tasks such as lineage tracing or genetic screens. For such applications, a barcode library would ideally have high diversity (many unique barcodes), non-destructive identification (repeated measurements in the same cells or population), and fast, inexpensive readout (many cells and conditions). Current nucleic acid barcoding methods generate high diversity but require destructive and slow/expensive readout, and current fluorescence barcoding methods are non-destructive, fast, and inexpensive to readout but lack high diversity. We recently proposed theory for how fluorescent protein combinations may generate a high-diversity barcode library with non-destructive, fast and inexpensive identification. Here, we present an initial experimental proof-of-concept by generating a library of ~150 barcodes from two-way combinations of 18 fluorescent proteins. We use a pooled cloning strategy to generate a barcode library that is validated to contain every possible combination of the 18 fluorescent proteins. Experimental results using single mammalian cells and spectral flow cytometry demonstrate excellent classification performance of individual fluorescent proteins, with the exception of mTFP1, and of most evaluated barcodes, with many true positive rates >99%. The library is compatible with genetic screening for hundreds of genes (or gene pairs) and lineage tracing hundreds of clones. This work lays a foundation for greater diversity libraries (potentially ~10 5 and more) generated from hundreds of spectrally-resolvable tandem fluorescent protein probes.

Geographical Origin Traceability of Atractylodis Macrocephalae Rhizoma Based on Chemical Composition, Chromaticity, and Electronic Nose.

Atractylodis Macrocephalae Rhizoma (AMR) is a traditional Chinese medicine used for gastrointestinal diseases. With increased demand, there are more and more places of cultivation for AMR. However, the quality of AMR varies from place to place, and there is no good way to distinguish AMR from different origins at present. In this paper, we determined the content of eight chemical components including 60% ethanol extracts, essential oil, polysaccharides, atractylenolides, and atractylone, obtained the color parameters of AMR powder by colorimetry, and odor information was captured by the electronic nose, all of which were combined with machine learning to establish a rapid origin traceability method. The results of the principal component analysis of the chemical components revealed that Zhejiang AMR has a high comprehensive score and overall better quality. The Kruskal-Wallis test demonstrated that there are varying degrees of differences in chemical composition and color parameters across the different origin. However, the accuracy of the classification model is low (less than 80%), making it difficult to distinguish between different origins of AMR. The electronic nose demonstrated excellent classification performance in the traceability of AMR from different origins, with accuracy reaching more than 90% (PLS-DA: 96.88%, BPNN: 96.88%, PSO-SVM: 100%). Overall, this study clarified the quality differences of AMR among different origins, and a rapid and precise method combining machine learning was developed to trace the origin of AMR.

PRO-SMOTEBoost: An adaptive SMOTEBoost probabilistic algorithm for rebalancing and improving imbalanced data classification

In the field of data mining and machine learning, dealing with imbalanced datasets is one of the most complex problems. The class imbalance issue significantly affects the classification of minority classes when using common classification algorithms. These algorithms often prioritize improving the performance of the majority class at the expense of the minority class, leading to misclassifying negative instances as positive ones. To address this problem, the Synthetic Minority Over-sampling Technique (SMOTE) has gained popularity to rebalance imbalanced data for classification. However, in this paper, we propose two algorithms to enhance the performance of imbalanced classification further. The first algorithm is PRO-SMOTE, an improvement over SMOTE. PRO-SMOTE relies on conditional probabilities to effectively rebalance imbalanced classes and improve the predictive performance metrics satisfactorily and reliably. By considering conditional probabilities, PRO-SMOTE can reduce the majority classes and optimally increase the minority class. Second, the PRO-SMOTEBoost algorithm, in turn, is based on the PRO-SMOTE to overcome classification anomalies and problems encountered by machine learning algorithms during classification, especially the weak ones. PRO-SMOTEBoost aims to maximize predictive precision to the greatest extent possible by combining the strengths of PRO-SMOTE with boosting techniques. Evaluating these algorithms using traditional machine learning algorithms such as Random Forests, C4.5, Naive Bayes, and Support Vector Machines has demonstrated excellent classification results. The performance metrics, encompassing F1-score, G-means, Precision, Accuracy, Recall, AUC-ROC, and Precision-Recall-curves, achieved by the proposed algorithm demonstrate a range that extends from over 90% to a flawless score of 100%. Compared to using these traditional algorithms individually, the utilization of PRO-SMOTEBoost has shown a significant improvement of 10% to 40% in performance metrics. Overall, the proposed algorithms, PRO-SMOTE and PRO-SMOTEBoost, offer effective solutions to address the challenges posed by imbalanced datasets. They provide improved predictive metrics and demonstrate their superiority when compared to traditional even modern machine learning algorithms.

Generative Adversarial Autoencoder Integration Voting Algorithm Based on Mass Spectrometry Data

Mass spectrometry technology is often used in disease prevention and diagnosis and treatment. However, the number of mass spectrometry data features is huge and the features vary greatly between different diseases, making multi-disease diagnosis. The task of judgment is complex and difficult. To address the above problems, this paper proposes a generative adversarial autoencoder integrated voting algorithm msDAGVote based on mass spectrometry data.The generative adversarial network based on dual autoencoders is used as the feature extraction framework of msDAGVote. After inputting mass spectrometry data for training, the generator subnetwork is used for feature extraction.Finally, the constructed features were screened by integrating the voting feature selection algorithm, and the optimal feature subset was used for multi-disease diagnosis.The results were evaluated on mass spectrometry datasets of different disease types. The experimental data showed that the features extracted by msDAGVote outperformed the comparison methods and significantly reduced the classification time.The required number of features and excellent disease classification and diagnosis capabilities are required. The classification AUC exceeds 0.98 on 6 datasets and The set exceeds 0.87.

A multi-class fundus disease classification system based on an adaptive scale discriminator and hybrid loss

Fundus images are crucial in the observation and detection of ophthalmic diseases. However, detecting multiple ophthalmic diseases from fundus images using deep learning techniques is a complex and challenging task One challenge is the complexity of fundus disease structures, which leads to low detection accuracy. Another challenge is the class imbalance problem common in multi-label image classification, which increases the difficulty of algorithm training and evaluation. To address these issues, this study leverages deep learning to propose an ophthalmic disease classification system. We first employ ResNet50 as the backbone network to extract image features, and then use our designed multi-dimensional attention module and adaptive scale discriminator to enhance the network's ability to detect disease features. During training, we innovatively propose a hybrid loss function method to improve the detection capability on imbalanced data. Finally, we conducted experiments on the ODRI-5K dataset with the proposed classification system. In the test set, our method achieved an AUC of 98.53 and an F1-score of 89.73. This result fully demonstrates the excellent disease classification capability of our method. In summary, the multi-label fundus image disease classification system we proposed exhibits outstanding recognition capability, providing an effective solution for the diagnosis of multi-label fundus image diseases.

Research on fault diagnosis for three-phase rectifier device in direct current transmission system based on continuous wavelet transform and vision transformer

Abstract As a core component of photovoltaic power generation systems, the three-phase rectifier device plays a crucial role, and its failure can potentially reduce energy conversion efficiency and output quality. Presently, the performance of fault time-domain signal diagnosis methods based on three-phase rectifier circuits is challenging to enhance. This paper proposes a novel fault detection method for three-phase rectifier devices based on Vision Transformer, referred to as CWT-ViT, to address this issue. This method transforms time-domain fault signals into images through Continuous Wavelet Transform (CWT), subsequently inputting these images into a Vision Transformer model. Relying on its powerful self-attention mechanism and fully connected layers, it realizes the extraction and learning of rectifier device image features. A Simulink simulation model of a three-phase bridge controllable rectifier circuit is established for fault injection to collect fault signals. Fault diagnosis experiments demonstrate that the proposed diagnostic method achieves a prediction accuracy of 98.6%, maintaining a relatively high precision level. In comparison to four excellent classification models currently available: AlexNet, RepVGG, ResNet, and GoogLeNet, the proposed method demonstrates superior diagnostic performance. Additionally, this paper conducts ablation experiments to meticulously analyze the impact of each module in the fault diagnosis process. This research achieves more precise and efficient fault diagnosis in photovoltaic power generation systems, thereby reducing downtime and maintenance costs for actual equipment and enhancing the stability of photovoltaic power generation systems. This research provides an innovative, intelligent solution for the intelligent operations and maintenance of photovoltaic power generation.

Strategies for identifying adulterated Acanthopanax senticosus using portable mass spectrometry and chemometrics

Acanthopanax senticosus is widely cultivated in China, Japan, South Korea, and Russia, and is extensively researched worldwide. Illegal activities, particularly adulteration have been fostered due to its large market demand and high price. This study successfully identifies authentic and adulterated Acanthopanax senticosus samples using a portable mass spectrometer combined with chemometrics. Different data processing and feature selection methods were evaluated for authenticity and adulteration models, with SNV-VIP being selected as the optimal method for both models. Excellent classification performance was achieved using Orthogonal Partial Least Squares Discriminant Analysis (OPLS-DA), K-nearest Neighbors (KNN), Random Forest (RF), and Convolutional Neural Networks-Long Short-Term Memory-Attention (CNN-LSTM-Attention) models, with prediction accuracies for the authenticity model validation set being 1.00, 1.00, 1.00, and 1.00, respectively. The prediction accuracies for the adulteration model validation set were 0.86, 0.73, 0.89, and 0.92, respectively. Additionally, the models identified the most important ions based on variable importance. The combination of portable mass spectra (PMS) and chemometrics provides a simple, rapid, and reliable method for identifying adulteration in Acanthopanax senticosus samples. This study provides a new basis into the application of PMS for adulteration detection in the food field.

B-123 Prediction of Opioid Use Duration in Post-Surgical Orthopedic Patients Using CYP2D6 Inhibitor Index and Routine Laboratory Markers

Abstract Background Hydrocodone, the most commonly prescribed opioid in the U.S., is typically used for pain management following surgery and is a known potential drug of abuse with non-negligible risk of addiction. Significant variability in patients’ response to hydrocodone therapy have been reported, owing to both iatrogenic and endogenous sources. The objective of this study is to evaluate the feasibility of predicting post-discharge hydrocodone use in patients who have undergone orthopedic surgery using patient demographics, genotyping, concurrently prescribed medications, and routinely collected laboratory test results. Methods Targeted genotyping was performed on each patient with genes known to affect hydrocodone pharmacokinetics or pharmacodynamics, including CYP2D6, CYP3A4, CYP3A5, CYP2B6, COMT, OPRM1, and ABCB1. An inhibition index for CYP2D6 was calculated by ranking concurrently prescribed medications as weak, moderate, or strong inhibitors of enzyme activity. Pain index, average hydrocodone dose per day during hospital stay, and CYP2D6 estimated activity scores based on allele functionality were included as predictors. In addition, a retrospective chart review of electronic hospital records was performed where basic metabolic panel and complete blood count results were screened within 10 days of each patient's surgery date. Two types of classification and decision tree algorithms were tuned and validated as prediction models using 5-fold cross validation, including a ‘Fast and Frugal Decision Tree’ (FFTree) and an extreme gradient boosting machine (xgBoost). Clinical predictive features were ranked according to the Shapley Additive Explanations (SHAP) values using the xgBoost model. Results Out of 79 total patients with hydrocodone use duration information, 25 were categorized as “Short” and 54 categorized as “Long” using a 1-week threshold. FFTree model selected the top three features of CYP2D6 inhibition index, blood sodium level, and blood creatinine level and obtained a sensitivity and specificity of 0.80 and 0.76, respectively. The xgBoost model, using the same three features, achieved a sensitivity and specificity of 0.872 and 0.628, respectively, an AUROC of 0.814, PRAUC of 0.912, net benefit of 0.359, and was well-calibrated with a Brier score of 0.161. Consistent with previously published results, the predictive capacity of all genotypes analyzed were unremarkable and consistently ranked as the least important features by the xgBoost model SHAP values, due to their low predictive value. Conclusions Both the FFTree and xgBoost models were able to adequately classify the patients according to a 1-week stratification criteria with good to excellent classification performance. Patients with larger CYP2D6 inhibition index were more likely to be classified as “Long” duration. Sodium and creatinine level, which may reflect hydration status and renal function, and therefore hydromorphone elimination rate, were key predictors of post-discharge hydrocodone use duration when combined with the CYP2D6 inhibition index. Further refinement of the proposed models and validation of model robustness and stability using external cohorts is necessary. These results may have implications for providers when prescribing hydrocodone for pain management, where the ability to risk-stratify patients according to their predicted probability of developing opioid use disorder is of clinical importance.

A [formula omitted]-means triangular synthesis large margin classifier with unified pinball loss for imbalanced data

Large Margin Distribution Machine (LDM) improves the Support Vector Machine (SVM) by integrating the marginal distribution of samples into the objective function, which exhibits excellent classification and generalization performance. However, most of the existing LDM-based models exhibit inherent flaws: (1) The assumption of a category uniform distribution, resulting in an inability to effectively address the issue of class imbalance. (2) The inheritance of the hinge loss in SVM, leading to inferior anti-noise performance. Given the shortcomings above, this paper constructs a novel K-means Triangular Synthesis (KTS) method for imbalanced data classification and introduces Unified Pinball (UP) loss to ensure robust performance, demonstrated as a novel KTS large margin classifier with UP Loss (KTS-UPLMC) model. Specifically, the KTS method utilizes the triangular synthesis and generates samples based on the cluster density, effectively mitigating the problems of introducing noise samples and strip-shaped sample distribution in the traditional synthetic minority oversampling technique, further alleviating the LDM’s classification line offset. In addition, the UP Loss considers quantile distance, improving the anti-noise performance of the model. Comparative experiments on artificial datasets and benchmark datasets validate the effectiveness and noise resistance of the proposed KTS-UPLMC in imbalanced data classification problems. Furthermore, the stability of the KTS-UPLMC is substantiated by the parameter sensitivity analysis experiment. In conclusion, the KTS method effectively addresses category imbalance, while the integration of the UP Loss enhances noise resistance.

Investigating the detection of peanuts in chopped nut products using hyperspectral imaging systems

The intentional presence or cross-contamination of peanuts in other nut products can result in severe health problems for consumers allergic to peanuts. It is therefore essential to identify the presence of these allergenic compounds in commercialized nut products prior to their sale. For this purpose, we assessed the performance of a visible near infrared (Vis-NIR) and a shortwave infrared (SWIR) hyperspectral imaging (HSI) systems working in the spectral regions 419-1007 nm and 842-2532 nm, respectively, to identify peanut pieces in different chopped nuts (almonds, hazelnuts and walnuts). Two strategies were evaluated to create the training and validation sets. In Strategy I, these sets were composed of spectra belonging to individual pixels, whereas in Strategy II, the mean spectrum of each individual piece of nut was used. We used partial least squares discriminant analysis (PLS-DA) to develop the classification models, and the results were assessed by means of the values obtained for the sensitivity, specificity, and non-error rate (NER) statistics. The external validation procedure showed excellent classification results, with a NER of 98.3 % and 99.8 % for the Vis-NIR and SWIR systems, respectively, for Strategy I, and 100 % for both systems when Strategy II was followed. These results therefore confirm the viability of using HSI technology together with multivariate classification methods to detect peanut pieces in other chopped-nut products.

Assessment of fish health status for waterless transportation based on image features and deep learning models

In the current aquaculture industry, the detection of physiological stress indicators in fish during waterless transportation is considered to be an effective method to monitor their health status. However, commonly used detection methods are invasive and interfere with the accuracy of detection results. In order to solve this problem, this study takes grouper as an example, combines multi-sensor physiological stress indicators monitoring, and designs a health status assessment and classification model based on image features and deep learning models, which inputs real-time fish image feature information data acquired during low-temperature waterless transportation into the optimised CNN-BiGRU classification model based on whale optimisation algorithm (WOA) proposed in this study, so as to achieve an accurate assessment of the health status of the fish. By inputting the image feature datasets based on time series and classified into the WOA-CNN-BiGRU, BiGRU, and GRU classification models for training, validation, and testing, respectively, the effectiveness of the classification performance of the models was verified by using accuracy, precision, recall and F1-value composite scores as the metrics. It was found that the WOA-CNN-BiGRU model had excellent classification performance, followed by the BiGRU and GRU models, especially in classifying the health status assessment of small size grouper. This study proposes an efficient and inexpensive method for real-time monitoring and accurate assessment of the health status of fish during waterless transportation, and also provides a reference for vigour monitoring and health assessment of other similar aquatic products.

Skin lesion segmentation using deep learning algorithm with ant colony optimization

BackgroundSegmentation of skin lesions remains essential in histological diagnosis and skin cancer surveillance. Recent advances in deep learning have paved the way for greater improvements in medical imaging. The Hybrid Residual Networks (ResUNet) model, supplemented with Ant Colony Optimization (ACO), represents the synergy of these improvements aimed at improving the efficiency and effectiveness of skin lesion diagnosis.ObjectiveThis paper seeks to evaluate the effectiveness of the Hybrid ResUNet model for skin lesion classification and assess its impact on optimizing ACO performance to bridge the gap between computational efficiency and clinical utility.MethodsThe study used a deep learning design on a complex dataset that included a variety of skin lesions. The method includes training a Hybrid ResUNet model with standard parameters and fine-tuning using ACO for hyperparameter optimization. Performance was evaluated using traditional metrics such as accuracy, dice coefficient, and Jaccard index compared with existing models such as residual network (ResNet) and U-Net.ResultsThe proposed hybrid ResUNet model exhibited excellent classification accuracy, reflected in the noticeable improvement in all evaluated metrics. His ability to describe complex lesions was particularly outstanding, improving diagnostic accuracy. Our experimental results demonstrate that the proposed Hybrid ResUNet model outperforms existing state-of-the-art methods, achieving an accuracy of 95.8%, a Dice coefficient of 93.1%, and a Jaccard index of 87.5.ConclusionThe addition of ResUNet to ACO in the proposed Hybrid ResUNet model significantly improves the classification of skin lesions. This integration goes beyond traditional paradigms and demonstrates a viable strategy for deploying AI-powered tools in clinical settings.Future workFuture investigations will focus on increasing the version's abilities by using multi-modal imaging information, experimenting with alternative optimization algorithms, and comparing real-world medical applicability. There is also a promising scope for enhancing computational performance and exploring the model's interpretability for more clinical adoption.

A dendrimer-based platform integrating surface-enhanced Raman scattering and class-incremental learning for rapidly detecting four pathogenic bacteria

Rapid monitoring of pathogens is crucial for preventing foodborne diseases, thus making it an urgent need to develop efficient, fast, and simple methods for on-site detection of multiple pathogens. With advances in SERS-based label-free biosensors and machine learning, progress is evident, yet challenges such as complex substrates and limited model interpretability persist. In this work, we reported a novel dendrimer-based platform that integrated surface-enhanced Raman scattering (SERS) with class-incremental learning (CIL) for quick and simultaneous detection of four pathogenic bacteria, namely Escherichia coli, Salmonella Paratyphi B, Pseudomonas aeruginosa, and Staphylococcus aureus. First, the poly(amidoamine) (PAMAM)-based gold nanoassemblies on silicon wafer (PGNAs/Si) was designed as a highly active SERS substrate with an easy fabrication process. Compared with naked gold nanoparticles, both sensitivity and repeatability were improved by introducing a controllable dendritic nanostructure with ultra-small internal nanogaps. The detection limits of four pathogens in water, food, and dietary supplement matrices were all on the order of 10 CFU/mL. Subsequently, to analyze the complex SERS spectra and distinguish samples with different pathogens, CIL models were established using the light gradient boosting machine (LightGBM) algorithm. Notably, the discriminative models demonstrated excellent classification performance with an accuracy of over 93.44 %. Further, the SHapley Additive exPlanations (SHAP) method was utilized to identify the key SERS features in accurately discriminating different pathogens. Together, these results demonstrate that the dendrimer-based platform, by integrating SERS with CIL, can rapidly detect four pathogenic bacteria, underscoring its potential for food safety testing or quality monitoring in medical supplies manufacturing.

Segmentation Synergy with a Dual U-Net and Federated Learning with CNNRF Models for Enhanced Brain Tumor Analysis

Background: Brain tumours represent a diagnostic challenge, especially in the imaging area, where the differentiation of normal and pathologic tissues should be precise. The use of up-to-date machine learning techniques would be of great help in terms of brain tumor identification accuracy from MRI data. Objective: This research paper aims to check the efficiency of a federated learning method that joins two classifiers, such as convolutional neural networks (CNNs) and random forests (R.F.F.), with dual U-Net segmentation for federated learning. This procedure benefits the image identification task on preprocessed MRI scan pictures that have already been categorized. Methods: In addition to using a variety of datasets, federated learning was utilized to train the CNN-RF model while taking data privacy into account. The processed MRI images with Median, Gaussian, and Wiener filters are used to filter out the noise level and make the feature extraction process easy and efficient. The surgical part used a dual U-Net layout, and the performance assessment was based on precision, recall, F1-score, and accuracy. Results: The model achieved excellent classification performance on local datasets as CRPs were high, from 91.28% to 95.52% for macro, micro, and weighted averages. Throughout the process of federated averaging, the collective model outperformed by reaching 97% accuracy compared to those of 99%, which were subjected to different clients. The correctness of how data is used helps the federated averaging method convert individual model insights into a consistent global model while keeping all personal data private. Conclusion: The combined structure of the federated learning framework, CNN-RF hybrid model, and dual U-Net segmentation is a robust and privacypreserving approach for identifying MRI images from brain tumors. The results of the present study exhibited that the technique is promising in improving the quality of brain tumor categorization and provides a pathway for practical utilization in clinical settings.

Intuitionistic fuzzy least squares MLTSVM for noisy label data using label-specific features and local label correlation

The multilabel twin support vector machine (MLTSVM) has been widely applied to multilabel classification fields because of its excellent classification performance, but it has the following three disadvantages. (a) In practical classification tasks, due to human negligence or some objective factors, there are many data with noise labels. Noisy label data have a negative effect on generating classification hyperplanes. However, MLTSVM cannot effectively reduce the negative effects on noisy label data. (b) Each label has its own specific features. However, for each label, MLTSVM can only use the same feature representation for classification. Therefore, it cannot obtain the optimal classification results. (c) In multilabel classification problems, there is a general correlation among the labels. However, when MLTSVM constructs a classification hyperplane for each label, it ignores the label correlation information. To address the above disadvantages, in this paper, a novel algorithm is proposed the called intuitionistic fuzzy least squares MLTSVM for noisy label data using label-specific features and local label correlation (SFLLC-IFLSMLTSVM). First, SFLLC-IFLSMLTSVM constructs an intuitionistic fuzzy set for each label; second, SFLLC-IFLSMLTSVM exploits the membership and nonmembership degrees in the intuitionistic fuzzy set to filter out the samples with noise labels and then performs clustering analysis to extract the label-specific features and the structure information of samples; finally, SFLLC-IFLSMLTSVM mines the local label correlation information in the process of constructing classification hyperplanes and exploits the membership and nonmembership degrees to suppress the negative effects of noise labels. Extensive comparative experiments on multilabel datasets show that SFLLC-IFLSMLTSVM can efficiently handle the multilabel classification problems with noise labels.