scholarly journals Decision Confidence Assessment in Multi-Class Classification

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3834
Author(s):  
Michał Bukowski ◽  
Jarosław Kurek ◽  
Izabella Antoniuk ◽  
Albina Jegorowa
Keyword(s):  
User Preferences ◽  
Human Interaction ◽  
Classification Problems ◽  
Human Expert ◽  
Decision Confidence ◽  
Novel Approach ◽  
Confidence Assessment ◽  
Multi Class Classification ◽  
Confidence Functions ◽  
Number Of Classes

This paper presents a novel approach to the assessment of decision confidence when multi-class recognition is concerned. When many classification problems are considered, while eliminating human interaction with the system might be one goal, it is not the only possible option—lessening the workload of human experts can also bring huge improvement to the production process. The presented approach focuses on providing a tool that will significantly decrease the amount of work that the human expert needs to conduct while evaluating different samples. Instead of hard classification, which assigns a single label to each class, the described solution focuses on evaluating each case in terms of decision confidence—checking how sure the classifier is in the case of the currently processed example, and deciding if the final classification should be performed, or if the sample should instead be manually evaluated by a human expert. The method can be easily adjusted to any number of classes. It can also focus either on the classification accuracy or coverage of the used dataset, depending on user preferences. Different confidence functions are evaluated in that aspect. The results obtained during experiments meet the initial criteria, providing an acceptable quality for the final solution.

scholarly journals A New Model Averaging Approach in Predicting Credit Risk Default

Risks ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 114
Author(s):  
Paritosh Navinchandra Jha ◽  
Marco Cucculelli
Keyword(s):  
Machine Learning ◽  
Credit Risk ◽  
Model Averaging ◽  
Research Direction ◽  
Future Research ◽  
Classification Problems ◽  
Average Technique ◽  
Model Average ◽  
Novel Approach ◽  
Unbalanced Dataset

The paper introduces a novel approach to ensemble modeling as a weighted model average technique. The proposed idea is prudent, simple to understand, and easy to implement compared to the Bayesian and frequentist approach. The paper provides both theoretical and empirical contributions for assessing credit risk (probability of default) effectively in a new way by creating an ensemble model as a weighted linear combination of machine learning models. The idea can be generalized to any classification problems in other domains where ensemble-type modeling is a subject of interest and is not limited to an unbalanced dataset or credit risk assessment. The results suggest a better forecasting performance compared to the single best well-known machine learning of parametric, non-parametric, and other ensemble models. The scope of our approach can be extended to any further improvement in estimating weights differently that may be beneficial to enhance the performance of the model average as a future research direction.

scholarly journals Confidence interval for micro-averaged F1 and macro-averaged F1 scores

2021 ◽  
Author(s):  
Kanae Takahashi ◽  
Kouji Yamamoto ◽  
Aya Kuchiba ◽  
Tatsuki Koyama
Keyword(s):  
Binary Classification ◽  
Classification Problem ◽  
Classification Problems ◽  
Summary Measure ◽  
Medical Field ◽  
Predictive Values ◽  
Binary Classification Problem ◽  
Multi Class Classification ◽  
Sensitivity Specificity ◽  
Measures Of Performance

AbstractA binary classification problem is common in medical field, and we often use sensitivity, specificity, accuracy, negative and positive predictive values as measures of performance of a binary predictor. In computer science, a classifier is usually evaluated with precision (positive predictive value) and recall (sensitivity). As a single summary measure of a classifier’s performance, F1 score, defined as the harmonic mean of precision and recall, is widely used in the context of information retrieval and information extraction evaluation since it possesses favorable characteristics, especially when the prevalence is low. Some statistical methods for inference have been developed for the F1 score in binary classification problems; however, they have not been extended to the problem of multi-class classification. There are three types of F1 scores, and statistical properties of these F1 scores have hardly ever been discussed. We propose methods based on the large sample multivariate central limit theorem for estimating F1 scores with confidence intervals.

scholarly journals Fuzzy Nominal Classification using Bipolar Analysis

2016 ◽  
pp. 233-253 ◽  
Author(s):  
Ayeley P. Tchangani
Keyword(s):  
Decision Making ◽  
Multi Criteria Decision Making ◽  
Classification Problems ◽  
Final Choice ◽  
Chain Management ◽  
Two Measures ◽  
Classification Procedures ◽  
Number Of Classes ◽  
A Company ◽  
Economic Domain

The process of assigning objects (candidates, projects, decisions, options, etc.) characterized by multiple attributes or criteria to predefined classes characterized by entrance conditions or constraints constitutes a subclass of multi-criteria decision making problems known as nominal or non-ordered classification problems as opposed to ordinal classification. In practice, class entrance conditions are not perfectly defined; they are rather fuzzily defined so that classification procedures must be design up to some uncertainty degree (doubt, indecision, imprecision, etc.). The purpose of this chapter is to expose recent advances related to this issue with particular highlights on bipolar analysis that consists in considering for a couple of object and class, two measures: classifiability measure that measures to what extent the former object can be considered for inclusion in the later class and rejectability measure, a degree that measures the extent to which one should avoid including this object into that class rendering final choice flexible and robust as many classes may be qualified for inclusion of an object. This apparent theoretical subject finds applications in almost any socio-economic domain and particularly in digital marketing. An application to supply chain management, where a certain number of potential suppliers of a company are to be classified in a number of classes in order to apply the appropriate strategic treatment to them, will be considered for illustration purpose.

Age Classification Based on Feature Fusion

2014 ◽  
Vol 519-520 ◽  
pp. 644-650
Author(s):  
Mian Shui Yu ◽  
Yu Xie ◽  
Xiao Meng Xie
Keyword(s):  
Feature Fusion ◽  
Principal Component ◽  
Directional Pattern ◽  
Gabor Wavelet ◽  
Support Vector ◽  
Classification Problems ◽  
Pca Method ◽  
Multi Class Classification ◽  
Global And Local ◽  
Fusion Theory

Age classification based on facial images is attracting wide attention with its broad application to human-computer interaction (HCI). Since human senescence is a tremendously complex process, age classification is still a highly challenging issue. In our study, Local Directional Pattern (LDP) and Gabor wavelet transform were used to extract global and local facial features, respectively, that were fused based on information fusion theory. The Principal Component Analysis (PCA) method was used for dimensionality reduction of the fused features, to obtain a lower-dimensional age characteristic vector. A Support Vector Machine (SVM) multi-class classifier with Error Correcting Output Codes (ECOC) was proposed in the paper. This was aimed at multi-class classification problems, such as age classification. Experiments on a public FG-NET age database proved the efficiency of our method.

MULTI-CLASS TRANSDUCTIVE CLASSIFICATION BASED ON LOCAL LEARNING AND ADJUSTABLE CLASS LABEL REPRESENTATION

2012 ◽  
Vol 26 (06) ◽  
pp. 1250014
Author(s):  
JIA LV ◽  
NAIYANG DENG
Keyword(s):  
Learning Problems ◽  
Local Learning ◽  
Classification Problems ◽  
Class Label ◽  
Transductive Learning ◽  
Good Classification ◽  
Density Relationship ◽  
Representation Method ◽  
Multi Class Classification

Local learning has been successfully applied to transductive classification problems. In this paper, it is generalized to multi-class classification of transductive learning problems owing to its good classification ability. Meanwhile, there is essentially no ordinal meaning in class label of multi-class classification, and it belongs to discrete nominal variable. However, common binary series class label representation has the equal distance from one class to another, and it does not reflect the sparse and density relationship among classes distribution, so a learning and adjustable nominal class label representation method is presented. Experimental results on a set of benchmark multi-class datasets show the superiority of our algorithm.

scholarly journals A procedure for meaningful unsupervised clustering and its application for solvent classification

2014 ◽  
Vol 12 (5) ◽  
pp. 594-603 ◽  
Author(s):  
Yaroslava Pushkarova ◽  
Yuriy Kholin
Keyword(s):  
Neural Networks ◽  
A Priori ◽  
Initial Distribution ◽  
C60 Fullerene ◽  
Classification Problems ◽  
Probabilistic Networks ◽  
Reliable Classification ◽  
Priori Information ◽  
Number Of Classes

AbstractArtificial neural networks have proven to be a powerful tool for solving classification problems. Some difficulties still need to be overcome for their successful application to chemical data. The use of supervised neural networks implies the initial distribution of patterns between the pre-determined classes, while attribution of objects to the classes may be uncertain. Unsupervised neural networks are free from this problem, but do not always reveal the real structure of data. Classification algorithms which do not require a priori information about the distribution of patterns between the pre-determined classes and provide meaningful results are of special interest. This paper presents an approach based on the combination of Kohonen and probabilistic networks which enables the determination of the number of classes and the reliable classification of objects. This is illustrated for a set of 76 solvents based on nine characteristics. The resulting classification is chemically interpretable. The approach proved to be also applicable in a different field, namely in examining the solubility of C60 fullerene. The solvents belonging to the same group demonstrate similar abilities to dissolve C60. This makes it possible to estimate the solubility of fullerenes in solvents for which there are no experimental data

Sign in / Sign up

Export Citation Format

Share Document