Multi Class Research Articles

Multi-Stage Classification Scheme to Optimize Medical Treatments

In most existing machine learning and deep learning settings, classification and regression prediction problems may be described as a process where the model output is based on a single-stage input. In most real-life scenarios achieving the desired medical state for the patient may involve dynamically solving drug prescription problems based on the input data at different stages, where each stage is a logical grouping such as timestep division, ICU stay, etc. Data at a given stage represents a recovery progression and can be fundamentally different from the datasets from the previous and future stages. Although A single model may solve the task, a multi-stage learning procedure may be more suitable. To solve this task, we propose an FNN-driven ensemble-based approach for predicting the medications that the patient should receive at each stage of the recovery process. The final medical discharge location is predicted as a result of sequential predictions of drugs and features. In this work, we combine model ensembling and multi-stage iterative learning for solving an optimal drug prescription generation task as a contribution to the existing literature.

Application of Long-Term Poverty Alleviation Mechanism in Chengde From the Perspective of Big Data Based on Computational Neural Model Fuzzy Algorithm

In order to consolidate the poverty alleviation achievements of impoverished counties, villages, and households, it is necessary to establish and improve stable poverty alleviation mechanisms. This article takes the Chengde region as the research object, and based on a large number of domestic and foreign poverty alleviation literature, combined with relevant poverty alleviation theories, uses fuzzy algorithms under big data to study and analyze the long-term mechanism of poverty alleviation and return prevention in the Chengde region. A multi classifier model with limited fuzzy rules is proposed to address the issues of low efficiency and long modeling time in existing fuzzy rule classification algorithms. When minimizing the cost function during model training, the cost function is fuzzy, thereby improving efficiency. The results indicate that the long-term poverty alleviation mechanism in Chengde from the perspective of fuzzy algorithm big data has profound strategic and theoretical significance for poverty alleviation.

Learning bayesian multinets from labeled and unlabeled data for knowledge representation

The Bayesian network classifiers (BNCs) learned from labeled training data are expected to generalize to fit unlabeled testing data based on the independent and identically distributed (i.i.d.) assumption, whereas the asymmetric independence assertion demonstrates the uncertainty of significance of dependency or independency relationships mined from data. A highly scalable BNC should form a distinct decision boundary that can be especially tailored to specific testing instance for knowledge representation. To address the issue of asymmetric independence assertion, in this paper we propose to learn k-dependence Bayesian multinet classifiers in the framework of multistage classification. By partitioning training set and pseudo training set according to high-confidence class labels, the dependency or independency relationships can be fully mined and represented in the topologies of the committee members. Extensive experimental results indicate that the proposed algorithm achieves competitive classification performance compared to single-topology BNCs (e.g., CFWNB, AIWNB and SKDB) and ensemble BNCs (e.g., WATAN, SA2DE, ATODE and SLB) in terms of zero-one loss, root mean square error (RMSE), Friedman test and Nemenyi test.

PCA based feature extraction and MPSO based feature selection for gene expression microarray medical data classification

In this paper, a novel Multi Class based Feature Extraction (MC-FE) method has been proposed for medical data classification. Genomic datasets, or gene expression-based microarray medical datasets, are categorised for cancer diagnosis. The first stage involves applying a feature extraction technique. The Principal Component Analysis (PCA) is used to extract the features for medical data classification to detect leukemia, colon tumors, and prostate cancer. The MPSO (modified particle swarm optimization) technique is used at the second stage to pick features from high-dimensional microarray medical datasets like prostate cancer, leukemia, and colon tumors. Finally, SVM, KNN, and Naive Bayes classifiers are used to classify medical data. Then, the classified data are stored in the cloud IOT sensors. When compared to the existing methods, the proposed method gives better optimized results for SVM, KNN, and Naive Bayes of 0.88, 0.86, and 0.73, respectively. The results of cancer data extraction and feature selection are also contrasted and assessed using certain performance measure factors.

Brain Tumor Detection and Multi Classification Using GNB-Based Machine Learning Approach

In an abnormal tissue called a brain tumor, the cells of the tumor reproduce quickly. if no control over tumor cell growth. The difficulties involved in identifying and treating brain tumors Machine learning is the most technologically sophisticated tool for classification and detection, implementing reliable state-of-the-art A.I. as well as neural network classification techniques, the use of this technology in early diagnosis detection of brain tumors can be accomplished successfully. it is well known that the segmentation method is capable of helping simply destroy the brain's abnormal tumor regions In order to segment and categorize brain tumors, this study suggests a multimodal approach involving machine learning and medical assistance. Noise can be seen in MRI images. To make the method for eliminating noise from images easier, a geometric mean is used later. The algorithms used to segment an image into smaller pieces are fuzzy c-means algorithms. Detection of a specific area of interest is made simpler by segmentation. The dimension reduction procedure is carried out using the GLCM. Photographic features are extracted using the GLCM algorithm. Then, using a variety of ML techniques, like as CNN, ANN, SVM, Gaussian NB, and Adaptive Boosting, the photos are categorized. The Gaussian NB method performs more effectively with regard to the identification and classification of brain tumors. The plasterwork work achieved 98.80 percent accuracy using GNB, RBF SVM.

A Unified Multi-Class Feature Selection Framework for Microarray Data.

In feature selection research, simultaneous multi-class feature selection technologies are popular because they simultaneously select informative features for all classes. Recursive feature elimination (RFE) methods are state-of-the-art binary feature selection algorithms. However, extending existing RFE algorithms to multi-class tasks may increase the computational cost and lead to performance degradation. With this motivation, we introduce a unified multi-class feature selection (UFS) framework for randomization-based neural networks to address these challenges. First, we propose a new multi-class feature ranking criterion using the output weights of neural networks. The heuristic underlying this criterion is that "the importance of a feature should be related to the magnitude of the output weights of a neural network". Subsequently, the UFS framework utilizes the original features to construct a training model based on a randomization-based neural network, ranks these features by the criterion of the norm of the output weights, and recursively removes a feature with the lowest ranking score. Extensive experiments on 15 real-world datasets suggest that our proposed framework outperforms state-of-the-art algorithms. The code of UFS is available at https://github.com/SVMrelated/UFS.git.

A Novel Developed Supervised Machine Learning System For Classification And Prediction of Software Faults Using NASA Dataset

The software systems of modern computers are extremely complex and versatile. Therefore, it is essential to regularly detect and correct software design faults. In order to devote resources effectively towards the creation of trustworthy software, software companies are increasingly engaging in the practise of predicting fault-prone modules in advance of testing. These software fault prediction methods rely on the thoroughness with which prior software versions' fault as well as related code has been retrievedTime, energy, and money are all saved as a result. Increases the company's initial success and bottom line greatly by satisfying its clientele. Numerous academics have poured into this area throughout the years in an effort to raise the bar for all software. Nowadays, The most often used approaches in this field are those based on machine learning (ML). The field of ML seeks to perfect software capable of evolving as well as adapting in response to fresh data. This paper introduces a fresh approach for doing ML by bringing together a number of different expert systems. In order to reach agreement on which aspects of a software system need to be tested, the proposed multi-classifier model pools the strengths of the most effective classifiers. Several top-performing classifiers for defect prediction are put through their paces in an experiential evaluation. We test our method on 16 publicly available datasets from the NASA Metric Data Programme (MDP) repository at the promise repository. Parameters of confusion, recall, precision, recognition accuracy, etc., are evaluated and contrasted with existing schemes in a software analysis performed with the help of the python simulation tool with findings. The experimental outcomes demonstrate that by combining LGBM, XGBoost, and Voting classifiers, using a multi classifier approach, we are capable to significantly improve software fault prediction performance. The results of the investigation show that the suggested method will lead to better practical outcomes in the prediction of device failures.

Analysis of Influencing Factors on the Willingness and Behavioral Consistency of Chinese Consumers to Purchase Tea via E-Commerce Platforms

Tea is a global economic crop. In the traditional sales model, the quality of tea is difficult to judge via external clues, and it basically relies on consumers to taste and experience it firsthand. However, currently, most e-commerce platforms can only provide consumers with product information and cannot provide experiential services, which strengthens consumers’ purchasing concerns and makes it difficult for them to take practical actions even if they have the desire to purchase tea online. Therefore, this article is based on a questionnaire survey of consumers in China, the world’s largest tea producing and selling country, using unordered multi classification logistic analysis data and calculating the marginal effect proportion of consistency occurrence. Through data analysis, it is shown that there is a serious inconsistency between consumers’ willingness and behavior in choosing online tea purchases. However, under the influence of some internal and external factors, there will also be positive changes; for example, the level of education, online shopping age, familiarity with tea, convenience, product diversification, online evaluation, and other variables will increase the motivation for consumers to convert their purchase intention into actual behavior. In addition, increasing the level of variables such as age, cultural association, cultural experience, convenience, information reliability, award-winning status, familiarity with tea, product diversity, online evaluation, and service attitude in online shopping can enhance consumers’ willingness to shop online and reduce extreme situations where there is neither intention nor behavior. This study provides evidence from a consumer perspective to enhance the efficiency of tea e-commerce marketing and proposes countermeasures and suggestions based on the research results, which could also provide ideas for marketing strategies for tea or other similar agricultural products.

Design of Scalability Enabled Low Cost Automatic Speaker Recognition System Using Light Weight Multistage Classifier

Protracted learning processes and dedicated computational power are the quality determinants in automatic speaker recognition (ASR). Conventionally, speakers are separately modelled using their acoustic features and surrounding environment features. Analytical speaker modelling via the Gaussian mixture model (GMM) and the Universal Background Model (UBM) is predominant over invariant speech condition models. A high number of speakers, fluctuated surroundings, and limited capacity processors are persisting performance barriers in both analytical and automatic ASR models. This paper argues on the ASR scalability approach which ensures fine model performance under a large number of speakers with varying biometrics. It also aimed to bridge performance-hindering barriers via using Light Weight Multistage classification. Consequently, 100% recognition accuracy could be achieved over three different databases of 12, 19, and 118 speakers.

Key Signatures of Prominence Materials and Category of Cold Materials Identified by Random Forest Classifier

The origin of cold materials identified by different criteria is unclear. They are highly suspected to be erupted prominences. However, some cold materials defined by charge depletion exist in both quiet solar wind and interplanetary coronal mass ejections (ICMEs). Recently, solar observations show failed prominence eruption in coronal mass ejections (CMEs) that the prominence sometimes did not propagate into interplanetary space. This work uses Random Forest Classifier (RFC), which is an interpretable supervised machine-learning algorithm to study the distinct signatures of prominence cold materials (PCs) compared to quiet solar wind (QSW) and ICMEs excluding cold materials (ICMEEs). Twelve physical features measured by ACE at 1 au and the monthly averaged sunspot number are used in this study. The measurements from ACE are proton moments, magnetic field component B z , He/H, He/O, Fe/O, mean charge of oxygen and carbon, C6+/C5, C6+/C4+, and O7+/O6+. According to the returned weights from RFC that are checked by support vector machine classifier, the most important in situ signatures of PCs are obtained. Next, the trained RFC is used to check the category of the cold materials not related to CME observations. The results show that most segments of the cold materials are from prominences, but four of them are possibly from ICMEEs; another one segment is possibly from QSW. The most distinct signatures of PCs are lower (C6+/C5+)/(O7+/O6+), proton temperature, and He/O. Considering the obvious overlaps on key physical features between QSW, ICMEEs, and PCs, the multifeature classifier shows an advantage in identifying them than solid criteria.

KDD on the CIFAR10 dataset by meta models for binary classification approaches through IP

An ensemble classifiers have been successfully applied to image classification problems. This research finds the efficiency of ensemble model on tiny images for real world problems based on the following metrics like accuracy, precision, recall, receiver operating characteristic curve (ROC), precision recall curve (PRC), kappa, F-Measure, MCC, performance analysis of deviations on like Bagging, Logit Boost (LB), Iterative Classifier Optimizer (ICO), Classification Via Regression (CVR), Multi Class Classifier Updateable (MCCU), and Random Committee (RC) of selected meta models. The RC gives best outcome compare with other models such as 90% of accuracy, 90% of precision, 0.90 of recall, 0.96 of ROC, 0.94 of PRC, 0.80 of kappa, 0.82 of MCC with low deviations. The ICO gives worst outcome compare with other models such as 65% of accuracy, 0.65 of precision, 0.65 of recall, 0.74 of ROC, and 0.74 of PRC with high deviations. This work finds and evolves that the Random Committee model performs well based on comparison of several metrics with other models.

Premature Infant Cry Classification via Deep Convolutional Recurrent Neural Network Based on Multi-class Features

Premature Infant Cry Classification via Deep Convolutional Recurrent Neural Network Based on Multi-class Features

Design of a Multi-Feature Classification Scheme for Infant Epileptic Seizures.

Neonatal epileptic seizures take place in the early childhood years, accounting for a severe condition with several deaths and neurological problems in newborn neonates. Despite the early advancements on the diagnosis and/or treatment of this condition, as a major difficulty accounts the inability of the physicians to identify and characterize a seizure, as one a small percentage gets detected in neonatal intensive care units (NICU). An important step towards any kind of seizure classification is the detection and reduction of non-cerebral activity. Towards this direction, our multi-feature approach contains spectral and statistical characteristics of EEG signals of 79 infants with suspicion of seizure and assesses the performance of two classification algorithms iteratively. The trained models (Support Vector Machine (SVM) and Random Forest classifiers) yielded high classification performance (>80% and >85% respectively). A robust neonatal seizure classification scheme is thus proposed, along with nine high scoring spectrum and statistical features. The importance of embedding an artefact reduction approach is also discussed, since the complex artifacts spread throughout the signals have great impact on the accuracy of the algorithms. The nine extracted high scoring spectral and statistical features might be used as potential biomarkers for neonatal seizure prediction in a clinical setting.

A NOVEL APPROACH TO BANKNOTE CLASSIFICATION USING TRANSFER LEARNING

Banknote classification is a fundamental component of financial system architecture. Recognition as well as verifying the integrity of banknotes is extremely important for secure transactions at financial institutions. A highly precise multi-classification model can be created using deep learning along with an extensive image dataset of these currency notes featuring them in a myriad of conditions. In addition to providing accuracy, this would also assist reduce the amount of manual intervention required, which would result in greater employee efficiency. This study involves the implementation of transfer learning on a publicly available image dataset of Indian and Thai banknotes. The results of the study will help create an automatic banknote identification and integrity verification layer in the transaction system architecture of financial institutions. KEYWORDS : Banknote Classification, Banknote Identification, Multi classification, Machine learning

Multi-Stage Classification of Retinal OCT Using Multi-Scale Ensemble Deep Architecture.

Accurate noninvasive diagnosis of retinal disorders is required for appropriate treatment or precision medicine. This work proposes a multi-stage classification network built on a multi-scale (pyramidal) feature ensemble architecture for retinal image classification using optical coherence tomography (OCT) images. First, a scale-adaptive neural network is developed to produce multi-scale inputs for feature extraction and ensemble learning. The larger input sizes yield more global information, while the smaller input sizes focus on local details. Then, a feature-rich pyramidal architecture is designed to extract multi-scale features as inputs using DenseNet as the backbone. The advantage of the hierarchical structure is that it allows the system to extract multi-scale, information-rich features for the accurate classification of retinal disorders. Evaluation on two public OCT datasets containing normal and abnormal retinas (e.g., diabetic macular edema (DME), choroidal neovascularization (CNV), age-related macular degeneration (AMD), and Drusen) and comparison against recent networks demonstrates the advantages of the proposed architecture's ability to produce feature-rich classification with average accuracy of 97.78%, 96.83%, and 94.26% for the first (binary) stage, second (three-class) stage, and all-at-once (four-class) classification, respectively, using cross-validation experiments using the first dataset. In the second dataset, our system showed an overall accuracy, sensitivity, and specificity of 99.69%, 99.71%, and 99.87%, respectively. Overall, the tangible advantages of the proposed network for enhanced feature learning might be used in various medical image classification tasks where scale-invariant features are crucial for precise diagnosis.

The relationship between fertility knowledge and unintended pregnancy: a survey among women of reproductive age in Shiraz, Iran

ABSTRACT Unintended pregnancy poses significant health risks for mothers, often leading to induced abortions. Understanding fertility is crucial when it comes to predicting the likelihood of unintended pregnancy. This study employed a quantitative research approach, utilizing a survey method. The survey was conducted in 2022 and involved 1065 married women aged 15–49 residing in Shiraz. The data collection process involved the administration of a standardized questionnaire. The sampling process utilized a combination of multi-stage classification and systematic random methods. The analysis of variable associations demonstrated a significant positive correlation between fertility knowledge, age, husband’s age, duration of marriage, and monthly income variables with the proportion of unintended pregnancies. It was observed that higher levels of education among both women and their husbands were associated with a lower proportion of unintended pregnancies. Additionally, employed women exhibited a significantly lower proportion of unintended pregnancies compared to non-employed women. The logistic regression analysis further confirmed that fertility knowledge and monthly income exerted a significant reverse influence on the likelihood of experiencing an unintended pregnancy. Lack of awareness regarding fertility knowledge among women can contribute to the occurrence of unintended pregnancies. Unintended pregnancies, in turn, can pose potential health risks for women.

Multi-Omic Integration of Blood-Based Tumor-Associated Genomic and Lipidomic Profiles Using Machine Learning Models in Metastatic Prostate Cancer.

To determine prognostic and predictive clinical outcomes in metastatic hormone-sensitive prostate cancer (mHSPC) and metastatic castrate-resistant prostate cancer (mCRPC) on the basis of a combination of plasma-derived genomic alterations and lipid features in a longitudinal cohort of patients with advanced prostate cancer. A multifeature classifier was constructed to predict clinical outcomes using plasma-based genomic alterations detected in 120 genes and 772 lipidomic species as informative features in a cohort of 71 patients with mHSPC and 144 patients with mCRPC. Outcomes of interest were collected over 11 years of follow-up. These included in mHSPC state early failure of androgen-deprivation therapy (ADT) and exceptional responders to ADT; early death (poor prognosis) and long-term survivors in mCRPC state. The approach was to build binary classification models that identified discriminative candidates with optimal weights to predict outcomes. To achieve this, we built multi-omic feature-based classifiers using traditional machine learning (ML) methods, including logistic regression with sparse regularization, multi-kernel Gaussian process regression, and support vector machines. The levels of specific ceramides (d18:1/14:0 and d18:1/17:0), and the presence of CHEK2 mutations, AR amplification, and RB1 deletion were identified as the most crucial factors associated with clinical outcomes. Using ML models, the optimal multi-omics feature combination determined resulted in AUC scores of 0.751 for predicting mHSPC survival and 0.638 for predicting ADT failure; and in mCRPC state, 0.687 for prognostication and 0.727 for exceptional survival. The models were observed to be superior than using a limited candidate number of features for developing multi-omic prognostic and predictive signatures. Using a ML approach that incorporates multiple omic features improves the prediction accuracy for metastatic prostate cancer outcomes significantly. Validation of these models will be needed in independent data sets in future.

Class-Independent Regularization for Learning with Noisy Labels

Training deep neural networks (DNNs) with noisy labels often leads to poorly generalized models as DNNs tend to memorize the noisy labels in training. Various strategies have been developed for improving sample selection precision and mitigating the noisy label memorization issue. However, most existing works adopt a class-dependent softmax classifier that is vulnerable to noisy labels by entangling the classification of multi-class features. This paper presents a class-independent regularization (CIR) method that can effectively alleviate the negative impact of noisy labels in DNN training. CIR regularizes the class-dependent softmax classifier by introducing multi-binary classifiers each of which takes care of one class only. Thanks to its class-independent nature, CIR is tolerant to noisy labels as misclassification by one binary classifier does not affect others. For effective training of CIR, we design a heterogeneous adaptive co-teaching strategy that forces the class-independent and class-dependent classifiers to focus on sample selection and image classification, respectively, in a cooperative manner. Extensive experiments show that CIR achieves superior performance consistently across multiple benchmarks with both synthetic and real images. Code is available at https://github.com/RumengYi/CIR.

A method for photoplethysmography signal quality assessment fusing multi-class features with multi-scale series information

Photoplethysmography (PPG) is often affected by interference, which could lead to incorrect judgment of physiological information. Therefore, performing a quality assessment before extracting physiological information is crucial. This paper proposed a new PPG signal quality assessment by fusing multi-class features with multi-scale series information to address the problems of traditional machine learning methods with low accuracy and deep learning methods requiring a large number of samples for training. The multi-class features were extracted to reduce the dependence on the number of samples, and the multi-scale series information was extracted by a multi-scale convolutional neural network and bidirectional long short-term memory to improve the accuracy. The proposed method obtained the highest accuracy of 94.21%. It showed the best performance in all sensitivity, specificity, precision, and F1-score metrics, compared with 6 quality assessment methods on 14 700 samples from 7 experiments. This paper provides a new method for quality assessment in small samples of PPG signals and quality information mining, which is expected to be used for accurate extraction and monitoring of clinical and daily PPG physiological information.

Skin Disease Prediction

Machine Learning (ML) is an emerging technology and a discipline to study how to use the machine to simulate human learning activities. It focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy. Prediction in ML involves using a trained model to make predictions on forecasts, about new unseen data based on patterns learned from past data. On the contrary healthcare plays an important role in human life. Healthcare presents a range of complex and challenging problems that require sophisticated solutions. For example, accurately diagnosing diseases based on medical images can be difficult, but ML models can be trained to identify subtle patterns that might be missed by human experts. Skin diseases are very common nowadays and spreading widely among people in present time. Therefore, development of data mining techniques can efficiently distinguish classes of skin disease is important. Due to lack of medical facilities available in the remote areas, patients usually ignore early symptoms which may worsen the situation as time progresses. Hence, there is a rising need for automatic skin disease detection system with high accuracy. Therefore, an application is developed which uses Convolutional Neural Network (CNN) as it is the most efficient algorithm for image classification. Then a machine learning model is built for better accuracy. Then Softmax is used for multi classification. Deep Learning is used to train the model, Deep Learning is a part of Machine Learning in which unlike Machine Learning it uses large dataset and hence the number of classifiers is reduced substantially. The final model will be able to identify and classify the type of disease which has affected a particular area of skin.