Multi-class Classification System Research Articles

Wireless capsule endoscopy multiclass classification using three-dimensional deep convolutional neural network model

BackgroundWireless capsule endoscopy (WCE) is a patient-friendly and non-invasive technology that scans the whole of the gastrointestinal tract, including difficult-to-access regions like the small bowel. Major drawback of this technology is that the visual inspection of a large number of video frames produced during each examination makes the physician diagnosis process tedious and prone to error. Several computer-aided diagnosis (CAD) systems, such as deep network models, have been developed for the automatic recognition of abnormalities in WCE frames. Nevertheless, most of these studies have only focused on spatial information within individual WCE frames, missing the crucial temporal data within consecutive frames.MethodsIn this article, an automatic multiclass classification system based on a three-dimensional deep convolutional neural network (3D-CNN) is proposed, which utilizes the spatiotemporal information to facilitate the WCE diagnosis process. The 3D-CNN model fed with a series of sequential WCE frames in contrast to the two-dimensional (2D) model, which exploits frames as independent ones. Moreover, the proposed 3D deep model is compared with some pre-trained networks. The proposed models are trained and evaluated with 29 subject WCE videos (14,691 frames before augmentation). The performance advantages of 3D-CNN over 2D-CNN and pre-trained networks are verified in terms of sensitivity, specificity, and accuracy.Results3D-CNN outperforms the 2D technique in all evaluation metrics (sensitivity: 98.92 vs. 98.05, specificity: 99.50 vs. 86.94, accuracy: 99.20 vs. 92.60). In conclusion, a novel 3D-CNN model for lesion detection in WCE frames is proposed in this study.ConclusionThe results indicate the performance of 3D-CNN over 2D-CNN and some well-known pre-trained classifier networks. The proposed 3D-CNN model uses the rich temporal information in adjacent frames as well as spatial data to develop an accurate and efficient model.

Real-time inspection and fault detection for large photovoltaic arrays based on drones and deep learning algorithms

In recent years, the installation of renewable energy generation systems based on photovoltaic (PV) panels has experienced massive increments and PV parks with thousands of panels are now becoming commonplace. Yet, there are some challenges, like inspection and fault detection. Lately, these operations have been approached using drones. This project adds the use of deep learning, more specifically proposes the convolutional neural network (CNN) algorithm, the YOLOv5 model and Real-Time Messaging Protocol (RTMP) protocol to achieve real-time detection of PV panels failures. The YOLOv5 model was trained by sets sorted into 9 different categories including fault and abnormal objects’ coverage. This multi-class classification system was investigated by a variety of evaluation indexes to show effectiveness and accuracy. The system was also examined with its different fault classes. The performance results demonstrate that the mean average precision could reach up to 98% with a good training set, confirming the feasibility of proposed approaches.

Multiclass Email Classification by Using Ensemble Bagging and Ensemble Voting

Email is a common communication technology in modern life. The more emails we receive, the more difficult and time consuming it is to sort them out. One solution to overcome this problem is to create a system using machine learning to sort emails. Each method of machine learning and data sampling result in different performance. Ensemble learning is a method of combining several learning models into one model to get better performance. In this study we tried to create a multiclass email classification system by combining learning models, data sampling, and several data classes to obtain the effect of Ensemble Bagging and Ensemble Voting methods on the performance of the macro average f1 score, and compare it with non-ensemble models. The results of this study show that the sensitivity of Naïve Bayes to imbalance data is helped by the Ensemble Bagging and Ensemble Voting method with ∆P (delta performance) of range 0.0001 – 0.0018. Logistic Regression has performance with Ensemble Bagging and Ensemble Voting by ∆P of range 0.0001-0.00015. Decision Tree has lowest performance compared to others with ∆P of -0.01

Multi-Class classification of prostate cancer MRI images based on UCLA score using RegNetY-320 model

Prostate cancer (PCa) is the most frequent non-skin cancer in males, and it represents a significant global healthcare problem. Another challenge is the development of an accurate classification model for the detection of PCa. As a result, developing an accurate classification model for PCa is extremely important and has potentially significant clinical implications. These models have the potential to boost the benefits of treatment while also increasing the likelihood of a patient's survival. The PCa is classified in this research based on the T2w magnetic resonance images (MRI), which are collected from the prostate dataset. In this work, a deep learning-based approach RegNetY-320 model is proposed to classify and detect the PCa. The RegNet model is a pre-trained deep transfer learning architecture, which is most commonly used for the image classification process. The proposed model is optimized using various optimizers, including Adam, AdaMax, SGD, RMSprop, Ftrl, and Nadam, and the optimized models are termed model-01 to model-06. For the evaluation, a multiclass classification system was employed to classify 845 patient records from a mpMRI dataset with a unique "UCLA" score of the ROI. Accuracy, precision, sensitivity, specificity, and the F1 score are all calculated based on the classification for the purpose of performance analysis. Finally, in accordance with the findings, the performances of the various proposed models are evaluated in order to determine their validity. When compared among proposed models, the proposed model RegNetY-320_Model-03 optimized using the RMSprop optimizer has obtained greater performance with 95.70 percent accuracy, which is the highest accuracy performance obtained in this research.

Multi Class Brain Cancer Prediction System Empowered with BRISK Descriptor

Magnetic Resonance Imaging (MRI) is one of the important resources for identifying abnormalities in the human brain. This work proposes an effective Multi-Class Classification (MCC) system using Binary Robust Invariant Scalable Keypoints (BRISK) as texture descriptors for effective classification. At first, the potential Region Of Interests (ROIs) are detected using features from the accelerated segment test algorithm. Then, non-maxima suppression is employed in scale space based on the information in the ROIs. The discriminating power of BRISK is examined using three machine learning classifiers such as k-Nearest Neighbour (kNN), Support Vector Machine (SVM) and Random Forest (RF). An MCC system is developed which classifies the MRI images into normal, glioma, meningioma and pituitary. A total of 3264 MRI brain images are employed in this study to evaluate the proposed MCC system. Results show that the average accuracy of the proposed MCC-RF based system is 99.62% with a sensitivity of 99.16% and specificity of 99.75%. The average accuracy of the MCC-kNN system is 93.65% and 97.59% by the MCC-SVM based system.

Novel cascade filter design of improved sparse low-rank matrix estimation and kernel adaptive filtering for ECG denoising and artifacts cancellation

ElectroCardioGram (ECG) signals are highly vulnerable to disturbances caused by noise and artifact sources which can degrade the ECG signal quality and increase the difficulty in obtaining reliable and accurate clinical interpretations for heart conditions. This paper introduces, for the first time, the Improved Sparse Low-Rank (ISLR) algorithm for suppressing white/colored noises, and the Kernel Recursive Least Squares with Approximate Linear Dependency (ALDKRLS) algorithm for eliminating various artifact sources. A novel automated multi-stage filter is introduced for suppressing artifact components in the first stage using ALDKRLS and eliminating noise sources in the subsequent stage using ISLR. The robustness of the suggested multi-stage filter is demonstrated by eliminating noise and artifact components individually and when both present concurrently using real ECG data. Experimental results elucidate the outstanding accuracy of the suggested framework in eliminating interference sources and keeping the essential and important characteristics of the original ECG data. Also, the application of the suggested framework in practical systems is examined by investigating a new efficient ECG multi-class classification system before and after suppressing noise and artifact interferences. Results show that the suggested framework manages not only to eliminate effectively noise and artifact components, but also to achieve very accurate ECG diagnosis results by maintaining the essential characteristics of the ECG signal that differentiate different heart disorders. This elucidates the usefulness of the proposed multi-stage filter as a promising preprocessing tool for obtaining high-resolution ECG data and consequently enhancing the diagnosis performance of several heart diseases.

Automated ECG multi-class classification system based on combining deep learning features with HRV and ECG measures

Electrocardiogram (ECG) serves as the gold standard for noninvasive diagnosis of several types of heart disorders. In this study, a novel hybrid approach of deep neural network combined with linear and nonlinear features extracted from ECG and heart rate variability (HRV) is proposed for ECG multi-class classification. The proposed system enhances the ECG diagnosis performance by combining optimized deep learning features with an effective aggregation of ECG features and HRV measures using chaos theory and fragmentation analysis. The constant-Q non-stationary Gabor transform technique is employed to convert the 1-D ECG signal into 2-D image which is sent to a pre-trained convolutional neural network structure, called AlexNet. The pair-wise feature proximity algorithm is employed to select the optimal features from the AlexNet output feature vector to be concatenated with the ECG and HRV measures. The concatenated features are sent to different types of classifiers to distinguish three distinct subjects, namely congestive heart failure, arrhythmia, and normal sinus rhythm (NSR). The results reveal that the linear discriminant analysis classifier has the highest accuracy compared to the other classifiers. The proposed system is investigated with real ECG data taken from well-known databases, and the experimental results show that the proposed diagnosis system outperforms other recent state-of-the-art systems in terms of accuracy 98.75%, specificity 99.00%, sensitivity of 98.18%, and computational time 0.15 s. This demonstrates that the proposed system can be used to assist cardiologists in enhancing the accuracy of ECG diagnosis in real-time clinical setting.

Deep Learning-Based Multi-Class Classification of Breast Digital Pathology Images.

IntroductionBreast cancer, one of the most common health threats to females worldwide, has always been a crucial topic in the medical field. With the rapid development of digital pathology, many scholars have used AI-based systems to classify breast cancer pathological images. However, most existing studies only stayed on the binary classification of breast lesions (normal vs tumor or benign vs malignant), far from meeting the clinical demand. Therefore, we established a multi-class classification system of breast digital pathology images based on AI, which is more clinically practical than the binary classification system.MethodsIn this paper, we adopted a two-stage architecture based on deep learning method and machine learning method for the multi-class classification (normal tissue, benign lesion, ductal carcinoma in situ, and invasive carcinoma) of breast digital pathological images.ResultsThe proposed approach achieved an overall accuracy of 86.67% at patch-level. At WSI-level, the overall accuracies of our classification system were 88.16% on validation data and 90.43% on test data. Additionally, we used two public datasets, the BreakHis and BACH, for independent verification. The accuracies our model obtained on these two datasets were comparable to related publications. Furthermore, our model could achieve accuracies of 85.19% on multi-classification and 96.30% on binary classification (non-malignant vs malignant) using pathology images of frozen sections, which was proven to have good generalizability. Then, we used t-SNE for visualization of patch classification efficiency. Finally, we analyzed morphological characteristics of patches learned by the model.ConclusionThe proposed two-stage model could be effectively applied to the multi-class classification task of breast pathology images and could be a very useful tool for assisting pathologists in diagnosing breast cancer.

Beyond one-against-all (OAA) and one-against-one (OAO): An exhaustive and parallel half-against-half (HAH) strategy for multi-class classification and applications to metabolomics

Urinary metabolomics coupled with GC-MS has become a leading technology in newborn screening. Because of non-specificity, complexity and high-variety in clinical characteristics and metabolomic profiling, the simultaneous detection of multiple inherited metabolic diseases (IMDs) is often challenging. As a substantial health problem, a competent chemometrics multi-class classification system for the early detection and diagnosis of IMDs would be advantageous. Beyond the commonly used binarization techniques of one-against-all (OAA) and one-against-one (OAO), an exhaustive and parallel half-against-half (EPHAH) decomposition is described in this study to deal with multi-class classification. For a K-class problem, EPHAH employs uniform class binary partition strategy to induce the binary classifier evaluating a half of K classes against the other half. With K-class problem exhaustively decomposed into all uniform binary partitions of K classes, EPHAH parallelly arranges the corresponding binary classifiers and aggregates their outputs to obtain the multi-class prediction using max-wins voting strategy. Based on orthogonal partial least squares discriminant analysis (OPLS-DA) with feature selection using particle swarm optimization (PSO) algorithm, EPHAH is investigated by GC-MS urinary metabolomics data among healthy controls and 9 most common IMDs. The results show that EPHAH enables a complete learning of the complex multi-class decision boundaries of 10 classes, exhibiting significant superiority in classification accuracies over OAA, OAO and traditional HAH. Meanwhile, compared with OAO using the same max-wins voting strategy, EPHAH gives an effective break of the tie problem in classification and enhanced resolution in votes.

Machine Learning Models Reveal the Importance of Clinical Biomarkers for the Diagnosis of Alzheimer's Disease.

Alzheimer's Disease (AD) is a neurodegenerative disease that causes complications with thinking capability, memory and behavior. AD is a major public health problem among the elderly in developed and developing countries. With the growth of AD around the world, there is a need to further expand our understanding of the roles different clinical measurements can have in the diagnosis of AD. In this work, we propose a machine learning-based technique to distinguish control subjects with no cognitive impairments, AD subjects, and subjects with mild cognitive impairment (MCI), often seen as precursors of AD. We utilized several machine learning (ML) techniques and found that Gradient Boosting Decision Trees achieved the highest performance above 84% classification accuracy. Also, we determined the importance of the features (clinical biomarkers) contributing to the proposed multi-class classification system. Further investigation on the biomarkers will pave the way to introduce better treatment plan for AD patients.

Physical Features and Deep Learning-based Appearance Features for Vehicle Classification from Rear View Videos

Currently, there are many approaches for vehicle classification, but there is no specific study on automated, rear view, and video-based robust vehicle classification. The rear view is important for intelligent transportation systems since not all states in the United States require a frontal license plate on a vehicle. The classification of vehicles, from their rear views, is challenging since vehicles have only subtle appearance differences and there are changing illumination conditions and the presence of moving shadows. In this paper, we present a novel multi-class vehicle classification system that classifies a vehicle into one of four possible classes (sedan, minivan, SUV, and a pickup truck) from its rear view video, using physical and visual features. For a given geometric setup of the camera on highways, we make physical measurements on a vehicle. These measurements include visual rear ground clearance, the height of the vehicle, and the distance between the license plate and the rear bumper. We call these distances as the physical features. The visual features, also called appearance-based features, are extracted using convolutional neural networks from the input images. We achieve a classification accuracy of 93.22% and 91.52% using physical and visual features, respectively. Furthermore, we achieve a higher classification accuracy of 94.81% by fusing both the features together. The results are shown on a dataset consisting of 1831 rear view videos of vehicles and they are compared with various approaches, including deep learning techniques.

AOCT-NET: a convolutional network automated classification of multiclass retinal diseases using spectral-domain optical coherence tomography images.

Since introducing optical coherence tomography (OCT) technology for 2D eye imaging, it has become one of the most important and widely used imaging modalities for the noninvasive assessment of retinal eye diseases. Age-related macular degeneration (AMD) and diabetic macular edema eye disease are the leading causes of blindness being diagnosed using OCT. Recently, by developing machine learning and deep learning techniques, the classification of eye retina diseases using OCT images has become quite a challenge. In this paper, a novel automated convolutional neural network (CNN) architecture for a multiclass classification system based on spectral-domain optical coherence tomography (SD-OCT) has been proposed. The system used to classify five types of retinal diseases (age-related macular degeneration (AMD), choroidal neovascularization (CNV), diabetic macular edema (DME), and drusen) in addition to normal cases. The proposed CNN architecture with a softmax classifier overall correctly identified 100% of cases with AMD, 98.86% of cases with CNV, 99.17% cases with DME, 98.97% cases with drusen, and 99.15% cases of normal with an overall accuracy of 95.30%. This architecture is a potentially impactful tool for the diagnosis of retinal diseases using SD-OCT images.

Developing a FHIR-based EHR phenotyping framework: A case study for identification of patients with obesity and multiple comorbidities from discharge summaries.

Standards-based clinical data normalization has become a key component of effective data integration and accurate phenotyping for secondary use of electronic healthcare records (EHR) data. HL7 Fast Healthcare Interoperability Resources (FHIR) is an emerging clinical data standard for exchanging electronic healthcare data and has been used in modeling and integrating both structured and unstructured EHR data for a variety of clinical research applications. The overall objective of this study is to develop and evaluate a FHIR-based EHR phenotyping framework for identification of patients with obesity and its multiple comorbidities from semi-structured discharge summaries leveraging a FHIR-based clinical data normalization pipeline (known as NLP2FHIR). We implemented a multi-class and multi-label classification system based on the i2b2 Obesity Challenge task to evaluate the FHIR-based EHR phenotyping framework. Two core parts of the framework are: (a) the conversion of discharge summaries into corresponding FHIR resources - Composition, Condition, MedicationStatement, Procedure and FamilyMemberHistory using the NLP2FHIR pipeline, and (b) the implementation of four machine learning algorithms (logistic regression, support vector machine, decision tree, and random forest) to train classifiers to predict disease state of obesity and 15 comorbidities using features extracted from standard FHIR resources and terminology expansions. We used the macro- and micro-averaged precision (P), recall (R), and F1 score (F1) measures to evaluate the classifier performance. We validated the framework using a second obesity dataset extracted from the MIMIC-III database. Using the NLP2FHIR pipeline, 1237 clinical discharge summaries from the 2008 i2b2 obesity challenge dataset were represented as the instances of the FHIR Composition resource consisting of 5677 records with 16 unique section types. After the NLP processing and FHIR modeling, a set of 244,438 FHIR clinical resource instances were generated. As the results of the four machine learning classifiers, the random forest algorithm performed the best with F1-micro(0.9466)/F1-macro(0.7887) and F1-micro(0.9536)/F1-macro(0.6524) for intuitive classification (reflecting medical professionals' judgments) and textual classification (reflecting the judgments based on explicitly reported information of diseases), respectively. The MIMIC-III obesity dataset was successfully integrated for prediction with minimal configuration of the NLP2FHIR pipeline and machine learning models. The study demonstrated that the FHIR-based EHR phenotyping approach could effectively identify the state of obesity and multiple comorbidities using semi-structured discharge summaries. Our FHIR-based phenotyping approach is a first concrete step towards improving the data aspect of phenotyping portability across EHR systems and enhancing interpretability of the machine learning-based phenotyping algorithms.

Sensors Driven AI-Based Agriculture Recommendation Model for Assessing Land Suitability.

The world population is expected to grow by another two billion in 2050, according to the survey taken by the Food and Agriculture Organization, while the arable area is likely to grow only by 5%. Therefore, smart and efficient farming techniques are necessary to improve agriculture productivity. Agriculture land suitability assessment is one of the essential tools for agriculture development. Several new technologies and innovations are being implemented in agriculture as an alternative to collect and process farm information. The rapid development of wireless sensor networks has triggered the design of low-cost and small sensor devices with the Internet of Things (IoT) empowered as a feasible tool for automating and decision-making in the domain of agriculture. This research proposes an expert system by integrating sensor networks with Artificial Intelligence systems such as neural networks and Multi-Layer Perceptron (MLP) for the assessment of agriculture land suitability. This proposed system will help the farmers to assess the agriculture land for cultivation in terms of four decision classes, namely more suitable, suitable, moderately suitable, and unsuitable. This assessment is determined based on the input collected from the various sensor devices, which are used for training the system. The results obtained using MLP with four hidden layers is found to be effective for the multiclass classification system when compared to the other existing model. This trained model will be used for evaluating future assessments and classifying the land after every cultivation.

A multi-class classification system for continuous water quality monitoring

The issue addressed in this exposition is the classification of multivariate data collected through different sensors for water quality monitoring. Multivariate data are sequences that have various attributes in every instance of the sequences. A few endeavours exist to address this issue; however, none of them has given full emphasis on continuous dataset. Another solution for this issue is to reduce the instances to a single attribute while losing significant information. Different arrangements address both the multivariate and the sequential part of the data yet give an un-versatile solution. The proposed algorithm is not only able to monitor continuous water quality, but it also produces a better classification model for other continuous datasets as well. Instead of decreasing the attributes of the dataset, we introduce three additional reference indicators which are dependent on the actual attributes. We compare the classification accuracy of our proposed algorithm with standard classification models. The proposed method gives better classification accuracy compared to existing methods.

Systematic Review of an Automated Multiclass Detection and Classification System for Acute Leukaemia in Terms of Evaluation and Benchmarking, Open Challenges, Issues and Methodological Aspects.

This study aims to systematically review prior research on the evaluation and benchmarking of automated acute leukaemia classification tasks. The review depends on three reliable search engines: ScienceDirect, Web of Science and IEEE Xplore. A research taxonomy developed for the review considers a wide perspective for automated detection and classification of acute leukaemia research and reflects the usage trends in the evaluation criteria in this field. The developed taxonomy consists of three main research directions in this domain. The taxonomy involves two phases. The first phase includes all three research directions. The second one demonstrates all the criteria used for evaluating acute leukaemia classification. The final set of studies includes 83 investigations, most of which focused on enhancing the accuracy and performance of detection and classification through proposed methods or systems. Few efforts were made to undertake the evaluation issues. According to the final set of articles, three groups of articles represented the main research directions in this domain: 56 articles highlighted the proposed methods, 22 articles involved proposals for system development and 5 papers centred on evaluation and comparison. The other taxonomy side included 16 main and sub-evaluation and benchmarking criteria. This review highlights three serious issues in the evaluation and benchmarking of multiclass classification of acute leukaemia, namely, conflicting criteria, evaluation criteria and criteria importance. It also determines the weakness of benchmarking tools. To solve these issues, multicriteria decision-making (MCDM) analysis techniques were proposed as effective recommended solutions in the methodological aspect. This methodological aspect involves a proposed decision support system based on MCDM for evaluation and benchmarking to select suitable multiclass classification models for acute leukaemia. The said support system is examined and has three sequential phases. Phase One presents the identification procedure and process for establishing a decision matrix based on a crossover of evaluation criteria and acute leukaemia multiclass classification models. Phase Two describes the decision matrix development for the selection of acute leukaemia classification models based on the integrated Best and worst method (BWM) and VIKOR. Phase Three entails the validation of the proposed system.

Automatic ICD-10 multi-class classification of cause of death from plaintext autopsy reports through expert-driven feature selection.

ObjectivesWidespread implementation of electronic databases has improved the accessibility of plaintext clinical information for supplementary use. Numerous machine learning techniques, such as supervised machine learning approaches or ontology-based approaches, have been employed to obtain useful information from plaintext clinical data. This study proposes an automatic multi-class classification system to predict accident-related causes of death from plaintext autopsy reports through expert-driven feature selection with supervised automatic text classification decision models.MethodsAccident-related autopsy reports were obtained from one of the largest hospital in Kuala Lumpur. These reports belong to nine different accident-related causes of death. Master feature vector was prepared by extracting features from the collected autopsy reports by using unigram with lexical categorization. This master feature vector was used to detect cause of death [according to internal classification of disease version 10 (ICD-10) classification system] through five automated feature selection schemes, proposed expert-driven approach, five subset sizes of features, and five machine learning classifiers. Model performance was evaluated using precisionM, recallM, F-measureM, accuracy, and area under ROC curve. Four baselines were used to compare the results with the proposed system.ResultsRandom forest and J48 decision models parameterized using expert-driven feature selection yielded the highest evaluation measure approaching (85% to 90%) for most metrics by using a feature subset size of 30. The proposed system also showed approximately 14% to 16% improvement in the overall accuracy compared with the existing techniques and four baselines.ConclusionThe proposed system is feasible and practical to use for automatic classification of ICD-10-related cause of death from autopsy reports. The proposed system assists pathologists to accurately and rapidly determine underlying cause of death based on autopsy findings. Furthermore, the proposed expert-driven feature selection approach and the findings are generally applicable to other kinds of plaintext clinical reports.

An ordinal classification approach for CTG categorization.

Evaluation of cardiotocogram (CTG) is a standard approach employed during pregnancy and delivery. But, its interpretation requires high level expertise to decide whether the recording is Normal, Suspicious or Pathological. Therefore, a number of attempts have been carried out over the past three decades for development automated sophisticated systems. These systems are usually (multiclass) classification systems that assign a category to the respective CTG. However most of these systems usually do not take into consideration the natural ordering of the categories associated with CTG recordings. In this work, an algorithm that explicitly takes into consideration the ordering of CTG categories, based on binary decomposition method, is investigated. Achieved results, using as a base classifier the C4.5 decision tree classifier, prove that the ordinal classification approach is marginally better than the traditional multiclass classification approach, which utilizes the standard C4.5 algorithm for several performance criteria.

Multiclass Classification Problem of Large-Scale Biomedical Meta-Data

One of the important data mining method in biomedical research is classification task. Recent advances in biomedicine provide opportunities for molecular biology, such as measurement of activity of thousands of molecular tissue biomarkers. For example we can use data of gene expression measured by DNA microarrays or RNA-Seq technique, DNA methylation levels measured by DNA methylation microarrays or protein and phosphoprotein levels measured by reverse phase protein array. A big problem in applying large-scale genomic and proteomic data for classification problem is the dimension of these data. In this work, we propose novel multiclass feature selection and classification system for merged data from different molecular biomedical techniques. However, when we merge these data the biggest problem is the huge number of features with a limited number of samples. For that reason the feature selection step is crucial in high dimension data classification problem. Our results have shown that integrated analysis with proper feature selection and classification techniques used for large-scale meta-data can improve the classification accuracy and feature selection stability index. We have proofed, that for merged data we observe significantly higher classification accuracy for the same number of selected features as for single technique dataset.

The Multiclass ROC Front method for cost-sensitive classification

This paper addresses the problem of learning a multiclass classification system that can suit to any environment. By that we mean that particular (imbalanced) misclassification costs are taken into account by the classifier for predictions. However, these costs are not well known during the learning phase in most cases, or may evolve afterwards. There is a need in that case to learn a classifier that can potentially suit to any of these costs in prediction phase. The learning method proposed in this work, named the Multiclass ROC Front (MROCF) method, responds to this issue by exploiting ROC-based tools through a multiobjective optimization process. While this type of ROC-based multiobjective optimization approach has been successfully used for two-class problems, it has never been proposed in real-world multiclass classification problems. Experiments led on several real-world datasets show that the MROCF method offers a major improvement over a cost-insensitive classifier and is competitive with the state-of-the-art cost-sensitive optimization method on all but one of the 20 datasets.