Multi-class Classification Method Research Articles

Sigmoni: classification of nanopore signal with a compressed pangenome index.

Improvements in nanopore sequencing necessitate efficient classification methods, including pre-filtering and adaptive sampling algorithms that enrich for reads of interest. Signal-based approaches circumvent the computational bottleneck of basecalling. But past methods for signal-based classification do not scale efficiently to large, repetitive references like pangenomes, limiting their utility to partial references or individual genomes. We introduce Sigmoni: a rapid, multiclass classification method based on the r-index that scales to references of hundreds of Gbps. Sigmoni quantizes nanopore signal into a discrete alphabet of picoamp ranges. It performs rapid, approximate matching using matching statistics, classifying reads based on distributions of picoamp matching statistics and co-linearity statistics, all in linear query time without the need for seed-chain-extend. Sigmoni is 10-100× faster than previous methods for adaptive sampling in host depletion experiments with improved accuracy, and can query reads against large microbial or human pangenomes. Sigmoni is the first signal-based tool to scale to a complete human genome and pangenome while remaining fast enough for adaptive sampling applications. Sigmoni is implemented in Python, and is available open-source at https://github.com/vshiv18/sigmoni.

Multiclass skin lesion classification using deep learning networks optimal information fusion

A serious, all-encompassing, and deadly cancer that affects every part of the body is skin cancer. The most prevalent causes of skin lesions are UV radiation, which can damage human skin, and moles. If skin cancer is discovered early, it may be adequately treated. In order to diagnose skin lesions with less effort, dermatologists are increasingly turning to machine learning (ML) techniques and computer-aided diagnostic (CAD) systems. This paper proposes a computerized method for multiclass lesion classification using a fusion of optimal deep-learning model features. The dataset used in this work, ISIC2018, is imbalanced; therefore, augmentation is performed based on a few mathematical operations. After that, two pre-trained deep learning models (DarkNet-19 and MobileNet-V2) have been fine-tuned and trained on the selected dataset. After training, features are extracted from the average pool layer and optimized using a hybrid firefly optimization technique. The selected features are fused in two ways: (i) original serial approach and (ii) proposed threshold approach. Machine learning classifiers are used to classify the chosen features at the end. Using the ISIC2018 dataset, the experimental procedure produced an accuracy of 89.0%. Whereas, 87.34, 87.57, and 87.45 are sensitivity, precision, and F1 score respectively. At the end, comparison is also conducted with recent techniques, and it shows the proposed method shows improved accuracy along with other performance measures.

Multi-class multi-label classification of social media texts for typhoon damage assessment: a two-stage model fully integrating the outputs of the hidden layers of BERT

ABSTRACT With the development of social media, it has become increasingly important to quickly and accurately identify social media texts related to disasters (e.g. typhoon) to aid in rescue and recovery efforts. Currently, multi-class classification and pre-trained language model Bidirectional Encoder Representations from Transformers (BERT) are widely used for text classification. However, most studies on typhoon damage classification are multi-class single-label, which contradicts to the reality that a social media text may correspond to multiple types of damage. Moreover, the outputs of the hidden layers of BERT are not fully utilized. This paper proposes a two-stage multi-class multi-label classification method for typhoon damage assessment by fully integrating the outputs of the hidden layers of BERT. In the first stage, sentence vectors are adopted to identify typhoon damage-related texts. In the second stage, word matrices are applied for multi-class multi-label classification to further classify the texts into five damage categories (i.e. transportation, public, electricity, forestry, and waterlogging). The two stages are trained end-to-end to identify typhoon damage from social media texts. Experiments on SinaWeibo texts during typhoon landfall in Chinese coastal regions demonstrate that the proposed method can effectively improve the accuracy of text classification and comprehensively assess typhoon damage.

Partial label learning for automated classification of single-cell transcriptomic profiles.

Single-cell RNA sequencing (scRNASeq) data plays a major role in advancing our understanding of developmental biology. An important current question is how to classify transcriptomic profiles obtained from scRNASeq experiments into the various cell types and identify the lineage relationship for individual cells. Because of the fast accumulation of datasets and the high dimensionality of the data, it has become challenging to explore and annotate single-cell transcriptomic profiles by hand. To overcome this challenge, automated classification methods are needed. Classical approaches rely on supervised training datasets. However, due to the difficulty of obtaining data annotated at single-cell resolution, we propose instead to take advantage of partial annotations. The partial label learning framework assumes that we can obtain a set of candidate labels containing the correct one for each data point, a simpler setting than requiring a fully supervised training dataset. We study and extend when needed state-of-the-art multi-class classification methods, such as SVM, kNN, prototype-based, logistic regression and ensemble methods, to the partial label learning framework. Moreover, we study the effect of incorporating the structure of the label set into the methods. We focus particularly on the hierarchical structure of the labels, as commonly observed in developmental processes. We show, on simulated and real datasets, that these extensions enable to learn from partially labeled data, and perform predictions with high accuracy, particularly with a nonlinear prototype-based method. We demonstrate that the performances of our methods trained with partially annotated data reach the same performance as fully supervised data. Finally, we study the level of uncertainty present in the partially annotated data, and derive some prescriptive results on the effect of this uncertainty on the accuracy of the partial label learning methods. Overall our findings show how hierarchical and non-hierarchical partial label learning strategies can help solve the problem of automated classification of single-cell transcriptomic profiles, interestingly these methods rely on a much less stringent type of annotated datasets compared to fully supervised learning methods.

Non-invasive glucose prediction and classification using NIR technology with machine learning

In this paper, a dual wavelength short near-infrared system is described for the detection of glucose levels. The system aims to improve the accuracy of blood glucose detection in a cost-effective and non-invasive way. The accuracy of the method is evaluated using real-time samples collected with the reference finger prick glucose device. A feed forward neural network (FFNN) regression method is employed to predict glucose levels based on the input data obtained from NIR technology. The system calculates glucose evaluation metrics and performs Surveillance error grid (SEG) analysis. The coefficient of determination R2 and mean absolute error are observed 0.99 and 2.49 mg/dl, respectively. Additionally, the system determines the root mean square error (RMSE) as 3.02 mg/dl. It also shows that the mean absolute percentage error (MAPE) is 1.94% and mean squared error (MSE) is 9.16 (mg/dl)2 for FFNN. The SEG analysis shows that the glucose values measured by the system fall within the clinically acceptable range when compared to the reference method. Finally, the system uses the multi-class classification method of the multilayer perceptron (MLP) and K-nearest neighbors (KNN) classifier to classify glucose levels with an accuracy of 99%.

A hybrid machine learning with process analytics for predicting customer experience in online insurance services industry

It is essential to innovate and improve service levels by predicting possible process outcomes due to the growth of online service providers. This study estimates the customer satisfaction level based on customer experience analysis. In doing so, we answer recent calls for research about a more thorough exploration of customer behavior using predictive process monitoring techniques. In particular, a hybrid framework of supervised/unsupervised machine learning methods is proposed to predict the outcomes of customers’ experiences while dealing with the problem of high intra-class variance. This problem occurs due to the large dispersion of traces identified in the customer journeys. In this regard, customer journeys are first matched with the event log format aiming to implement a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering technique based on the similarity between the customer journeys. After summarizing the journeys by removing low-value activities, the multi-class decision tree classification method is applied, and the level of customer satisfaction is predicted. Due to the imbalanced nature of the data, the oversampling for imbalanced classification is applied to achieve good results in accuracy indicators such as recall, precision, and F1-score. Finally, the proposed approach has been evaluated on a real-life event log, BPI Challenge 2016, to investigate unsatisfied customers. The results of the machine learning models on the test data show a high degree of accuracy in predicting customer dissatisfaction.

Machine Learning Based Open Switch Fault Detection and Localization of Inverters

The location and detection of switch faults is a crucial step in improving the dependability of inverters, which is a requirement for critical applications. This paper focuses on a machine learning-based approach for the open-switch fault detection system for cascaded H-bridge (CHB) multilevel inverters (MLI) used in high- and medium-power applications. Each switch failure is taken into account in this analysis, and the problem is used to model logically different machine learning algorithms, namely Gaussian Naive Bayes (GNB), support vector machines (SVM) and multinomial logistic regression (MLR) models for fault identification and localization based on multi-class classification (MCC) methods. This work includes the simulation and hardware-based data collection from five-level CHB-MLI and correlation-based selection of prominent features in the final dataset. The results of three MCC models for all possible combinations of predictors (features) prove that the mean voltage of bridges is the dominant feature for fault detection in the CHB inverter. Other major findings are machine learning-assisted fault identification and diagnosis is undoubtedly accurate and significantly more promising in condition monitoring and fault diagnosis in CHB-MLIs. The results reveal 100% accuracy in fault diagnosis. Therefore, the presented work confirms switch fault detection in CHB-MLI with mean value as dominant fault feature along with machine learning techniques simple, robust and accurate fault detection.

Transforming two-dimensional tensor networks into quantum circuits for supervised learning

There have been numerous quantum neural networks reported, but they struggle to match traditional neural networks in accuracy. Given the huge improvement of the neural network models’ accuracy by two-dimensional tensor network (TN) states in classical tensor network machine learning (TNML), it is promising to explore whether its application in quantum machine learning can extend the performance boundary of the models. Here, we transform two-dimensional TNs into quantum circuits for supervised learning. Specifically, we encode two-dimensional TNs into quantum circuits through rigorous mathematical proofs for constructing model ansätze, including string-bond states, entangled-plaquette states and isometric TN states. In addition, we propose adaptive data encoding methods and combine with TNs. We construct a tensor-network-inspired quantum circuit (TNQC) supervised learning framework for transferring TNML from classical to quantum, and build several novel two-dimensional TN-inspired quantum classifiers based on this framework. Finally, we propose a parallel quantum machine learning method for multi-class classification to construct 2D TNQC-based multi-class classifiers. Classical simulation results on the MNIST benchmark dataset show that our proposed models achieve the state-of-the-art accuracy performance, significantly outperforming other quantum classifiers on both binary and multi-class classification tasks, and beat simple convolutional classifiers on a fair track with identical inputs. The noise resilience of the models makes them successfully run and work in a real quantum computer.

Discriminative Regression With Adaptive Graph Diffusion.

In this article, we propose a new linear regression (LR)-based multiclass classification method, called discriminative regression with adaptive graph diffusion (DRAGD). Different from existing graph embedding-based LR methods, DRAGD introduces a new graph learning and embedding term, which explores the high-order structure information between four tuples, rather than conventional sample pairs to learn an intrinsic graph. Moreover, DRAGD provides a new way to simultaneously capture the local geometric structure and representation structure of data in one term. To enhance the discriminability of the transformation matrix, a retargeted learning approach is introduced. As a result of combining the above-mentioned techniques, DRAGD can flexibly explore more unsupervised information underlying the data and the label information to obtain the most discriminative transformation matrix for multiclass classification tasks. Experimental results on six well-known real-world databases and a synthetic database demonstrate that DRAGD is superior to the state-of-the-art LR methods.

Multiclass Classification With Fuzzy-Feature Observations: Theory and Algorithms.

The theoretical analysis of multiclass classification has proved that the existing multiclass classification methods can train a classifier with high classification accuracy on the test set, when the instances are precise in the training and test sets with same distribution and enough instances can be collected in the training set. However, one limitation with multiclass classification has not been solved: how to improve the classification accuracy of multiclass classification problems when only imprecise observations are available. Hence, in this article, we propose a novel framework to address a new realistic problem called multiclass classification with imprecise observations (MCIMO), where we need to train a classifier with fuzzy-feature observations. First, we give the theoretical analysis of the MCIMO problem based on fuzzy Rademacher complexity. Then, two practical algorithms based on support vector machine and neural networks are constructed to solve the proposed new problem. The experiments on both synthetic and real-world datasets verify the rationality of our theoretical analysis and the efficacy of the proposed algorithms.

A Novel and Effective Multi-Class Classification Method for Imbalanced Medical Transcriptions

Natural Language Processing (NLP) techniques are used to glean information from Electronic Health Records (EHR) for identifying patients with unique clinical characteristics and defining phenotypes. The classification of imbalanced datasets is also one of the vital concerns in medical diagnosis. We built an improved framework for automating the multi-class classification of imbalanced medical transcriptions [1] into 40 medical specialties, by creating a set of important phenotypes/features. We implemented and tested five machine learning models out of which Random Forest Classifier has achieved the highest performance of 0.99 F1 score (precision 0.99, recall 0.99) and roc-auc-score of 0.99 on test data.

Noise signature identification using mobile phones for indoor localization

Indoor localization is still nowadays a challenge with room to improve. Even though there are many different approaches that have evidenced as effective, most of them require specific hardware or infrastructure deployed along the building that can be discarded in many potential scenarios. Others that do not require such on-site infrastructure, like inertial navigation-based systems, entail certain accuracy problems due to the accumulation of errors. However, this error-accumulation can be mitigated using beacons that support the recalibration of the system. The more frequently beacons are detected, the smaller will be the accumulated error. In this work, we evaluate the use of the noise signature of the rooms of a building to pinpoint the current location of a low-cost Android device. Despite this strategy is not a complete indoor localization system (two rooms could share the same signature), it allows us to generate beacons automatically. The noise recorded by the device is preprocessed performing audio filtering, audio frame segmentation, and feature extraction. We evaluated binary (determining if the ambient sound recording belonged to a specific room) and multi-class (identifying which room an ambient noise recording belonged to by comparing it amongst the remaining 18 rooms from the original 19 rooms sampled) classification methods. Our results indicate that the two Stacking techniques and K-Nearest Neighbor (KNN) machine learning classifier are the most successful methods in binary classification with an average accuracy of 99.19%, 99,08%, and 99.04%. In multi-class classification the average accuracy for KNN is 90.77%, and 90.52% and 90.15% for both Voting techniques.

A GAN-Based Data Augmentation Method for Imbalanced Multi-Class Skin Lesion Classification

A GAN-Based Data Augmentation Method for Imbalanced Multi-Class Skin Lesion Classification

An Efficient Optimization Approach for Designing Machine Models Based on Combined Algorithm

Many intrusion detection algorithms that use optimization have been developed and are commonly used to detect intrusions. The process of selecting features and the parameters of the classifier are essential parts of how well an intrusion detection system works. This paper provides a detailed explanation and discussion of an improved intrusion detection method for multiclass classification. The proposed solution uses a combination of the modified teaching–learning-based optimization (MTLBO) algorithm, the modified JAYA (MJAYA) algorithm, and a support vector machine (SVM). MTLBO is used with supervised machine learning (ML) to select subsets of features. Selection of the fewest features possible without impairing the accuracy of the results in feature subset selection (FSS) is a multiobjective optimization issue. This paper presents MTLBO as a mechanism and investigates its algorithm-specific, parameter-free idea. This study used the modified JAYA (MJAYA) algorithm to optimize the C and gamma parameters of the support vector machine (SVM) classifier. When the proposed MTLBO-MJAYA-SVM algorithm was compared with the original TLBO and JAYA algorithms on a well-known intrusion detection dataset, it was found to outperform them significantly.

A meta-learning network method for few-shot multi-class classification problems with numerical data

The support vector machine (SVM) method is an important basis of the current popular multi-class classification (MCC) methods and requires a sufficient number of samples. In the case of a limited number of samples, the problem of over-learning easily occurs, resulting in unsatisfactory classification. Therefore, this work investigates an MCC method that requires only a small number of samples. During model construction, raw data are converted into two-dimensional form via preprocessing. Via feature extraction, the learning network is measured and the loss function minimization principle is considered to better solve the problem of learning based on a small sample. Finally, three examples are provided to illustrate the feasibility and effectiveness of the proposed method.

Comparative Analysis of Classification Models for Predicting Cancer Stage in a Chilean Cancer Center

This study aimed to develop a predictive model for cancer stage using data from a Chilean cancer registry. Several factors, including cancer type, patient age, medical history, and time delay between diagnosis and treatment, were examined to determine their association with cancer stage. Multiple supervised multi-class classification methods were tested, and the best-performing models were identified. The results showed that the random forest, SVM polynomial, and composite models performed well across different stages, although distinguishing between Stages II and III was more challenging. The most important features for predicting cancer stage were found to be cancer type, TNM variables, and diagnostic extension. Variables related to treatment timing and sequence also showed some importance. It was emphasized that the results of predictive models should be interpreted carefully to avoid overprediction or underprediction. Clinical context and additional information should be considered to enhance the accuracy of predictions. The small dataset and limitations in data availability posed challenges in accurately predicting cancer stage for different cancer types. Implementing the predictive model can have various benefits, including informing treatment decisions, assessing disease severity, and optimizing resource allocation. Further research and expansion of the model's scope were recommended to improve its performance and impact. Overall, the study emphasized the potential of predictive models in cancer staging and highlighted the need for ongoing advancements in this field.

Gestive: Evaluation of Multi-Class Classification Methods for Gesture Recognition to Improve Presentation Experience

Gesture recognition is able to transform how we interact with technology, including during presentations. We aim to classify slide-control gestures and create a model that allows users to add their personalized gestures to to control presentation com- mands. To avoid wasting time on capturing and training the model, we aim to construct a model with a short training time and high accuracy. We assessed the efficiency of various multi-class classification methods for gesture recognition in presentation settings. We compared K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree, Linear Discriminant Analysis (LDA), and Random Forest. The results demonstrated that KNN offers the shortest training time while maintaining high accuracy. The findings of this study provide a basis for future research on gesture recognition technology and its imple- mentation to improve presentation experience.

An Enhanced Support Vector Machine based Multiclass Classification Method For Crop Prediction

Crop type classification is a fundamental task in precision agriculture, enabling informed decision-making for crop management and resource allocation. Support Vector Machines (SVMs) have emerged as robust and effective tools for multi-class classification tasks. This study explores the application of SVM-based multi-class classification techniques to accurately categorize various crop types based on remote sensing data. he SVM algorithm is employed to create decision boundaries that maximize the margin between different crop classes while minimizing classification errors. To enhance classification performance, various kernel functions such as linear, polynomial, and radial basis function are evaluated to capture complex relationships within the data. The proposed SVM-based approach is compared with other commonly used classification methods to assess its superiority in terms of accuracy, precision, recall, and F1-score.

Don't Fear the Artificial Intelligence: A Systematic Review of Machine Learning for Prostate Cancer Detection in Pathology.

Automated prostate cancer detection using machine learning technology has led to speculation that pathologists will soon be replaced by algorithms. This review covers the development of machine learning algorithms and their reported effectiveness specific to prostate cancer detection and Gleason grading. To examine current algorithms regarding their accuracy and classification abilities. We provide a general explanation of the technology and how it is being used in clinical practice. The challenges to the application of machine learning algorithms in clinical practice are also discussed. The literature for this review was identified and collected using a systematic search. Criteria were established prior to the sorting process to effectively direct the selection of studies. A 4-point system was implemented to rank the papers according to their relevancy. For papers accepted as relevant to our metrics, all cited and citing studies were also reviewed. Studies were then categorized based on whether they implemented binary or multi-class classification methods. Data were extracted from papers that contained accuracy, area under the curve (AUC), or κ values in the context of prostate cancer detection. The results were visually summarized to present accuracy trends between classification abilities. It is more difficult to achieve high accuracy metrics for multiclassification tasks than for binary tasks. The clinical implementation of an algorithm that can assign a Gleason grade to clinical whole slide images (WSIs) remains elusive. Machine learning technology is currently not able to replace pathologists but can serve as an important safeguard against misdiagnosis.

Estimating vulnerability metrics with word embedding and multiclass classification methods

Estimating vulnerability metrics with word embedding and multiclass classification methods