Multi-class Classification Problem Research Articles

Facial Expression Recognition Using Convolutional Neural Network

Understanding others' intentions through nonverbal cues like facial emotions is crucial in human communication. To design and train Deep Learning Models, this paper describes in detail how Convolutional Neural Network Models are developed using tf. Keras. The aim is to Sort facial photos into one of the seven face detection classifiers, our model is developed in such a manner that it learns hidden nonlinearity from the entered facial images, which is vital for discriminating the form of emotion someone is expressing. The model proposed on the Lenet-5 architecture by Yann LeCun uses the subsampling, feature map, and activation function (ReLu) in between the convolutional layer and fully connected layer for the output soft-max activation function will be used. The FER-2013 dataset, which consists of 35,887 structured 48x48 pixel grayscale images, was used to train the CNN models. The training dataset has 28,709 elements, while the testing dataset has 3,589 elements, and while validation has 3,589 elements. Train and test are the two folder names used to organize the FER dataset. separated even further into distinct files, each holding a different kind of FER dataset class. To mitigate the overfitting of the dropout, batch normalization and the model are employed. Since this is a multiclass classification problem, we are utilizing the Soft-max activation function and the Rectified linear unit for non-linear operation (ReLu). We are training a categorical cross- entropy and matrix for accuracy based on the parameters to assess the constructed CNN model's performance by examining the training epoch history and we have used optimizer Adam (Adaptive Moment Estimation) with the learning rate of 0.0001. We obtained the accuracy of the LeNet-5 model on training at 95.49% and testing at 49.47% [13].

Automatic Spontaneous Speech Analysis for the Detection of Cognitive Functional Decline in Older Adults: Multilanguage Cross-Sectional Study.

The rise in life expectancy is associated with an increase in long-term and gradual cognitive decline. Treatment effectiveness is enhanced at the early stage of the disease. Therefore, there is a need to find low-cost and ecological solutions for mass screening of community-dwelling older adults. This work aims to exploit automatic analysis of free speech to identify signs of cognitive function decline. A sample of 266 participants older than 65 years were recruited in Italy and Spain and were divided into 3 groups according to their Mini-Mental Status Examination (MMSE) scores. People were asked to tell a story and describe a picture, and voice recordings were used to extract high-level features on different time scales automatically. Based on these features, machine learning algorithms were trained to solve binary and multiclass classification problems by using both mono- and cross-lingual approaches. The algorithms were enriched using Shapley Additive Explanations for model explainability. In the Italian data set, healthy participants (MMSE score≥27) were automatically discriminated from participants with mildly impaired cognitive function (20≤MMSE score≤26) and from those with moderate to severe impairment of cognitive function (11≤MMSE score≤19) with accuracy of 80% and 86%, respectively. Slightly lower performance was achieved in the Spanish and multilanguage data sets. This work proposes a transparent and unobtrusive assessment method, which might be included in a mobile app for large-scale monitoring of cognitive functionality in older adults. Voice is confirmed to be an important biomarker of cognitive decline due to its noninvasive and easily accessible nature.

SubGE-DDI: A new prediction model for drug-drug interaction established through biomedical texts and drug-pairs knowledge subgraph enhancement.

Biomedical texts provide important data for investigating drug-drug interactions (DDIs) in the field of pharmacovigilance. Although researchers have attempted to investigate DDIs from biomedical texts and predict unknown DDIs, the lack of accurate manual annotations significantly hinders the performance of machine learning algorithms. In this study, a new DDI prediction framework, Subgraph Enhance model, was developed for DDI (SubGE-DDI) to improve the performance of machine learning algorithms. This model uses drug pairs knowledge subgraph information to achieve large-scale plain text prediction without many annotations. This model treats DDI prediction as a multi-class classification problem and predicts the specific DDI type for each drug pair (e.g. Mechanism, Effect, Advise, Interact and Negative). The drug pairs knowledge subgraph was derived from a huge drug knowledge graph containing various public datasets, such as DrugBank, TwoSIDES, OffSIDES, DrugCentral, EntrezeGene, SMPDB (The Small Molecule Pathway Database), CTD (The Comparative Toxicogenomics Database) and SIDER. The SubGE-DDI was evaluated from the public dataset (SemEval-2013 Task 9 dataset) and then compared with other state-of-the-art baselines. SubGE-DDI achieves 83.91% micro F1 score and 84.75% macro F1 score in the test dataset, outperforming the other state-of-the-art baselines. These findings show that the proposed drug pairs knowledge subgraph-assisted model can effectively improve the prediction performance of DDIs from biomedical texts.

Text Classification and Cluster Analysis based on Deep Learning and Natural Language Processing

At present, the commonly used Bag of Words (BOW) expression ignores the semantic information of text and the problems of high dimension and high sparsity of feature extraction. This paper presents a multi-class text representation and classification algorithm. This project is based on the vector expression of keywords and takes the multi-category classification problem as the research object. Then, a hybrid Deep Location network (HDBN) is constructed by combining DBN with Boltzmann (DBM). Then, this paper does a lot of tests on the algorithm and proves the effectiveness of the algorithm. In addition, the 2D visual experiment is carried out with HDBN, and then the high-level text expression based on HDBN is obtained. The expression has strong cohesion and weak coupling.

Graph-Based Audio Classification Using Pre-Trained Models and Graph Neural Networks.

Sound classification plays a crucial role in enhancing the interpretation, analysis, and use of acoustic data, leading to a wide range of practical applications, of which environmental sound analysis is one of the most important. In this paper, we explore the representation of audio data as graphs in the context of sound classification. We propose a methodology that leverages pre-trained audio models to extract deep features from audio files, which are then employed as node information to build graphs. Subsequently, we train various graph neural networks (GNNs), specifically graph convolutional networks (GCNs), GraphSAGE, and graph attention networks (GATs), to solve multi-class audio classification problems. Our findings underscore the effectiveness of employing graphs to represent audio data. Moreover, they highlight the competitive performance of GNNs in sound classification endeavors, with the GAT model emerging as the top performer, achieving a mean accuracy of 83% in classifying environmental sounds and 91% in identifying the land cover of a site based on its audio recording. In conclusion, this study provides novel insights into the potential of graph representation learning techniques for analyzing audio data.

A Novel Validated Real-World Dataset for the Diagnosis of Multiclass Serous Effusion Cytology according to the International System and Ground-Truth Validation Data

Introduction: The application of artificial intelligence (AI) algorithms in serous fluid cytology is lacking due to the deficiency in standardized publicly available datasets. Here, we develop a novel public serous effusion cytology dataset. Furthermore, we apply AI algorithms on it to test its diagnostic utility and safety in clinical practice. Methods: The work is divided into three phases. Phase 1 entails building the dataset based on the multitiered evidence-based classification system proposed by the International System (TIS) of serous fluid cytology along with ground-truth tissue diagnosis for malignancy. To ensure reliable results of future AI research on this dataset, we carefully consider all the steps of the preparation and staining from a real-world cytopathology perspective. In phase 2, we pay special consideration to the image acquisition pipeline to ensure image integrity. Then we utilize the power of transfer learning using the convolutional layers of the VGG16 deep learning model for feature extraction. Finally, in phase 3, we apply the random forest classifier on the constructed dataset. Results: The dataset comprises 3,731 images distributed among the four TIS diagnostic categories. The model achieves 74% accuracy in this multiclass classification problem. Using a one-versus-all classifier, the fallout rate for images that are misclassified as negative for malignancy despite being a higher risk diagnosis is 0.13. Most of these misclassified images (77%) belong to the atypia of undetermined significance category in concordance with real-life statistics. Conclusion: This is the first and largest publicly available serous fluid cytology dataset based on a standardized diagnostic system. It is also the first dataset to include various types of effusions and pericardial fluid specimens. In addition, it is the first dataset to include the diagnostically challenging atypical categories. AI algorithms applied on this novel dataset show reliable results that can be incorporated into actual clinical practice with minimal risk of missing a diagnosis of malignancy. This work provides a foundation for researchers to develop and test further AI algorithms for the diagnosis of serous effusions.

A hybrid EEG classification model using layered cascade deep learning architecture.

The problem of multi-class classification is always a challenge in the field of EEG (electroencephalogram)-based seizure detection. The traditional studies focus on computing or learning a set of features from EEG to distinguish between different patterns. However, the extraction of characteristic information becomes increasingly difficult as the number of EEG types increases. To address this issue, a creative EEG classification technique is proposed by employing a principal component analysis network (PCANet) coupled with phase space reconstruction (PSR) and power spectrum density (PSD). We have introduced the PSR and PSD to prepare the inputs, where dynamic and frequency information are exposed from deep within PCANet. It is remarkable that a layered cascade strategy is designed to make a powerful deep learner according to the rule of one network vs one task (OVO). The proposed method has achieved greater effects than the individual models and shown superior performance in comparison with state-of-the-art algorithms, which present 98.0% of sensitivity, 99.90% of specificity, and 99.07% of accuracy. Our ensemble PCANet model works in an assembly line-like manner, obviating the need for hand-craft features. Results demonstrate that the proposed scheme can greatly enhances the accuracy and robustness of seizure detection from EEG signals.

Disease Prediction Using Machine Learning Methods

A visit to the doctor’s office usually starts with the nurse collecting patient symptoms, health information, and necessary lab tests. All the information will be presented to the doctor, and the doctor may collect additional information in order to do the right diagnosis. The doctor’s brain is like a complicated machine capable of quick processing of the information, relating it to previous patients, and mapping the information to diagnoses. This process resembles much to how machine learning works. In this article, we explore how machine learning could help predict different diseases and facilitate a doctor’s diagnosis. In particular, our study focuses on unbalanced, multiclass classification problems.

A distance-based kernel for classification via Support Vector Machines.

Support Vector Machines (SVMs) are a type of supervised machine learning algorithm widely used for classification tasks. In contrast to traditional methods that split the data into separate training and testing sets, here we propose an innovative approach where subsets of the original data are randomly selected to train the model multiple times. This iterative training process aims to identify a representative data subset, leading to improved inferences about the population. Additionally, we introduce a novel distance-based kernel specifically designed for binary-type features based on a similarity matrix that efficiently handles both binary and multi-class classification problems. Computational experiments on publicly available datasets of varying sizes demonstrate that our proposed method significantly outperforms existing approaches in terms of classification accuracy. Furthermore, the distance-based kernel achieves superior performance compared to other well-known kernels from the literature and those used in previous studies on the same datasets. These findings validate the effectiveness of our proposed classification method and distance-based kernel for SVMs. By leveraging random subset selection and a unique kernel design, we achieve notable improvements in classification accuracy. These results have significant implications for diverse classification problems in Machine Learning and data analysis.

Measuring Resampling Methods on Imbalanced Educational Dataset’s Classification Performance

Imbalanced data refers to a condition that there is a different size of samples between one class with another class(es). It made the term “majority” class that represents the class with more instances number on the dataset and “minority” classes that represent the class with fewer instances number on the dataset. Under the target of educational data mining which demands accurate measurement of the student’s performance analysis, data mining requires an appropriate dataset to produce good accuracy. This study aims to measure the resampling method’s performance through the classification process on the student’s performance dataset, which is also a multi-class dataset. Thus, this study also measures how the method performs on a multi-class classification problem. Utilizing four public educational datasets, which consist of the result of an educational process, this study aims to get a better picture of which resampling methods are suitable for that kind of dataset. This research uses more than twenty resampling methods from the SMOTE variants library. as a comparison; this study implements nine classification methods to measure the performance of the resampled data with the non-resampled data. According to the results, SMOTE-ENN is generally the better resampling method since it produces a 0,97 F1 score under the Stacking classification method and the highest among others. However, the resampling method performs relatively low on the dataset with wider label variations. The future work of this study is to dig deeper into why the resampling method cannot handle the enormous class variation since the F1 score on the student dataset is lower than the other dataset.

Deep Neural Networks for HER2 Grading of Whole Slide Images with Subclasses Levels

HER2 overexpression is a prognostic and predictive factor observed in about 15% to 20% of breast cancer cases. The assessment of its expression directly affects the selection of treatment and prognosis. The measurement of HER2 status is performed by an expert pathologist who assigns a score of 0, 1, 2+, or 3+ based on the gene expression. There is a high probability of interobserver variability in this evaluation, especially when it comes to class 2+. This is reasonable as the primary cause of error in multiclass classification problems typically arises in the intermediate classes. This work proposes a novel approach to expand the decision limit and divide it into two additional classes, that is 1.5+ and 2.5+. This subdivision facilitates both feature learning and pathology assessment. The method was evaluated using various neural networks models capable of performing patch-wise grading of HER2 whole slide images (WSI). Then, the outcomes of the 7-class classification were merged back into 5 classes in accordance with the pathologists’ criteria and to compare the results with the initial 5-class model. Optimal outcomes were achieved by employing colour transfer for data augmentation, and the ResNet-101 architecture with 7 classes. A sensitivity of 0.91 was achieved for class 2+ and 0.97 for 3+. Furthermore, this model offers the highest level of confidence, ranging from 92% to 94% for 2+ and 96% to 97% for 3+. In contrast, a dataset containing only 5 classes demonstrates a sensitivity performance that is 5% lower for the same network.

Automatic evaluation of the Nine-Hole Peg Test in multiple sclerosis patients using machine learning models

Neurological damage in Multiple Sclerosis (MS) affects the motor, sensory, visual, cognitive and sphincteric systems, resulting in different degrees of disability. Upper limb dysfunction is a core deficit affecting MS patients. However, since upper limb function impairment is not properly recorded in the Expanded Disability Status Scale (EDSS) for MS, other tests have been developed in the last decades. The Nine Hole Peg Test (9HPT) is widely considered a gold standard metric for manual dexterity. Unfortunately, its quantification strongly depends on the subjectivity of each clinician.The aim of this work is to standardize the measurement process of the 9HPT. Instead of a human interpretation of the time needed to complete the exercise, this paper aims to objectively extract multiple kinematic information of the subject’s hand (period, velocity, time). This information is used to detect the presence and the state of the disease more accurately and classify the patients automatically. The manuscript describes a developed framework to automate and objectivize the 9HPT. The framework evaluates the performance of different Machine Learning models and Artificial Neural Networks on MS diagnosis. The built system analyzes videos of subjects performing the 9HPT, extracts the hand’s pose using Convolutional Neural Networks, acquires the hand’s kinematic features and classifies the severity of the disease using Machine Learning algorithms. For the framework validation, two classification approaches are proposed. The first one is a binary classification problem, separating the subjects between control and patients. The second one is a multiclass classification problem, where the patients are separated into three different classes based on the severity assessed by the clinicians. A technical validation has been implemented with an accuracy of up 96.67% for the binary classification and 92.22% for the multiclass classification.

Ensemble methods of rank-based trees for single sample classification with gene expression profiles

Building Single Sample Predictors (SSPs) from gene expression profiles presents challenges, notably due to the lack of calibration across diverse gene expression measurement technologies. However, recent research indicates the viability of classifying phenotypes based on the order of expression of multiple genes. Existing SSP methods often rely on Top Scoring Pairs (TSP), which are platform-independent and easy to interpret through the concept of “relative expression reversals”. Nevertheless, TSP methods face limitations in classifying complex patterns involving comparisons of more than two gene expressions. To overcome these constraints, we introduce a novel approach that extends TSP rules by constructing rank-based trees capable of encompassing extensive gene-gene comparisons. This method is bolstered by incorporating two ensemble strategies, boosting and random forest, to mitigate the risk of overfitting. Our implementation of ensemble rank-based trees employs boosting with LogitBoost cost and random forests, addressing both binary and multi-class classification problems. In a comparative analysis across 12 cancer gene expression datasets, our proposed methods demonstrate superior performance over both the k-TSP classifier and nearest template prediction methods. We have further refined our approach to facilitate variable selection and the generation of clear, precise decision rules from rank-based trees, enhancing interpretability. The cumulative evidence from our research underscores the significant potential of ensemble rank-based trees in advancing disease classification via gene expression data, offering a robust, interpretable, and scalable solution. Our software is available at https://CRAN.R-project.org/package=ranktreeEnsemble.

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.

Nonparametric plug‐in classifier for multiclass classification of S.D.E. paths

AbstractWe study the multiclass classification problem where the features come from a mixture of time‐homogeneous diffusions. Specifically, the classes are discriminated by their drift functions while the diffusion coefficient is common to all classes and unknown. In this framework, we build a plug‐in classifier which relies on nonparametric estimators of the drift and diffusion functions. We first establish the consistency of our classification procedure under mild assumptions and then provide rates of convergence under different set of assumptions. Finally, a numerical study supports our theoretical findings.

A novel redistribution-based feature selection for text classification

Text classification is the process of automatically categorizing text documents into predefined labels, gaining increasing importance with the growing volume of data. In the vector space model, terms within documents must be quantified to be used with classifiers. The abundance of unique terms associated with documents can lead to unwieldy vectors. To address this issue, feature selection, reducing the number of terms by removing irrelevant terms, is a common solution. In this paper, a novel feature selection method called Amount of ReDistribution to Establish Neutrality, ARDEN, is proposed for the task of text classification. ARDEN, is designed with statistical distance perspective by measuring the distance of a term to its neutral counterpart, which represents the least distinguishing term having uniform document frequencies across all classes. ARDEN introduces a method to measure the related distance, providing insights into the degree of deviation of the term from neutrality, thus capturing its distinguishing power. ARDEN is experimentally tested against state-of-the-art feature selection methods. The results suggest that it is a competitive feature selection method, exhibiting superior performance in terms of summary statistics, μ and δ′. Furthermore, ARDEN is designed for multi-class text classification problems, which does not require a globalization function. Additionally, the proposed method is compared against Wasserstein statistical distance metric, and clearly outperforms it. Finally, we also propose δ′ evaluation criterion in order to facilitate the interpretation of experimental outcomes across multiple feature sizes.

Analyzing and assessing explainable AI models for smart agriculture environments

We analyze a case study in the field of smart agriculture exploiting Explainable AI (XAI) approach, a field of study that aims to provide interpretations and explanations to the behaviour of AI systems. The study regards a multiclass classification problem on the Crop Recommendation dataset. The original task is the prediction of the most adequate crop, according to seven features. In addition to the predictions, two of the most well-known XAI approaches have been used in order to obtain explanations and interpretations of the behaviour of the models: SHAP (SHapley Additive ExPlanations), and LIME (Local Interpretable Model-Agnostic Explanations). Both packages provide easy-to-understand visualizations that allow common users to understand explanations of single predictions even without going into the mathematical details of the algorithms. Within the scientific community criticisms have been raised against these approaches, and recently some papers brought to light some weaknesses. However, the two algorithms are among the most popular in XAI and are still considered points of reference for this field of study.

A novel classification method for GPR B-scan images based on weak-shot learning

Ground Penetrating Radar (GPR) is extensively employed for underground target detection, and the advancements in this domain have been hastened by the utilization of deep learning methodologies. Despite advancements in deep learning, practical engineering applications often face challenges in meeting the demanding requirements of large-scale data and high data quality. In this study, based on cross-domain transfer learning, we proposed a method for underground target classification of weak labeled GPR data. It combined strongly annotated source domain data with weakly annotated target domain data through adversarial learning to leverage the prior knowledge from existing large datasets and addressed the classification problem of small-sample GPR data. By employing adversarial learning to integrate strongly labeled source domain data with weakly labeled target domain data, we leverage prior knowledge from existing large datasets, thereby enhancing classification accuracy on a small GPR dataset. This approach reduces the requirements for annotation quality and sample quantity in the GPR B-scan dataset of underground targets. Additionally, it exhibits robustness to label noise, making it applicable to real-world GPR data classification tasks. Compared to some well-known networks, the proposed model achieved the best classification performance in multiclass classification problems, with an accuracy of 87.62% and an F1macro score of 87.60% on the test set. These results represent an improvement of 17.14 and 17.20 percentage points, respectively, over the best-performing classical classification networks. Additionally, the proposed model's reliability in cross-domain transfer learning, even with limited data, was substantiated through a comparison with other few-shot learning networks.

CPS Attack Detection under Limited Local Information in Cyber Security: An Ensemble Multi-Node Multi-Class Classification Approach

Cybersecurity breaches are common anomalies for distributed cyber-physical systems (CPS). However, the cyber security breach classification is still a difficult problem, even using cutting-edge artificial intelligence (AI) approaches. In this article, we study a multi-class classification problem in cyber security for attack detection. A challenging multi-node data-censoring case is considered. In such a case, data within each data center/node cannot be shared while the local data is incomplete. Particularly, local nodes contain only a part of the multiple classes. In order to train a global multi-class classifier without sharing the raw data across all nodes, we design a multi-node multi-class classification ensemble approach which is the main result of our study. By gathering the estimated parameters of the binary classifiers and data densities from each local node, the missing information for each local node is completed to build the global multi-class classifier. Numerical experiments are given to validate the effectiveness of the proposed approach under the multi-node data-censoring case. Under such a case, we even show the out-performance of the proposed approach over the full-data approach.

Milling cutter fault diagnosis using unsupervised learning on small data: A robust and autonomous framework

Tool condition affects the tolerances and the energy consumption and hence needs to be monitored. Artificial intelligence based data-driven techniques for tool condition determination are proposed. Unfortunately, the data-driven techniques are data-hungry. This paper proposes a methodology for classification based on unsupervised learning using limited unlabeled training data. The work presents a multi-class classification problem for the tool condition monitoring. The principal component analysis (PCA) is employed for dimensionality reduction and the principal components (PCs) are used as input for classification using k-means clustering. New collected data is then projected on the PC space, and classified using the clusters from the training. The methodology has been applied for classification of tool faults in 6 classes. The use of limited input parameters from the user makes the method ideal for monitoring a large number of machines with minimal intervention. Furthermore, due to the small amount of data needed for the training, the method has the potential to be transferable.