scispace - formally typeset
Search or ask a question
Topic

Classifier chains

About: Classifier chains is a research topic. Over the lifetime, 170 publications have been published within this topic receiving 20989 citations.


Papers
More filters
Dissertation
01 Dec 2016
TL;DR: This chapter discusses the development of classifier chains in multi-label classification and some of the methods used to achieve this goal.
Abstract: ...................................................................................................................... iii List of figures ............................................................................................................. vii List of tables................................................................................................................ ix List of appendices ....................................................................................................... xi List of abbreviations and/or acronyms ................................................................... xii CHAPTER 1: Introduction ........................................................................................ 1 1.1 Background ................................................................................................... 1 1.2 Notation ......................................................................................................... 2 1.3 Overview ....................................................................................................... 2 CHAPTER 2: Multi-label classification .................................................................... 4 2.1 Classification hierarchy ................................................................................ 4 2.2 Complexity of multi-label datasets ............................................................... 6 2.3 Objectives when analysing multi-label datasets ........................................... 7 2.4 Label dependence .......................................................................................... 8 2.5 Multi-label evaluation measures ................................................................. 10 2.6 Different approaches to multi-label classification ...................................... 13 2.7 Probem transformation methods ................................................................. 14 2.7.1 Binary relevance ................................................................................. 14 2.7.2 Label powerset .................................................................................... 15 2.7.3 Pairwise methods ................................................................................ 17 CHAPTER 3: Classifier chains in multi-label classification................................. 19 3.1 Classifier chains .......................................................................................... 19 3.2 Modifications of classifier chains ............................................................... 22 3.2.1 Ensemble of classifier chains .............................................................. 23 3.2.2 1-Classifier chains .............................................................................. 23 3.2.3 Limitations of the classifier chains-based methods ............................ 28 3.3 Lclassifier chains ...................................................................................... 30 Stellenbosch University https://scholar.sun.ac.za
Book ChapterDOI
01 Jan 2021
TL;DR: In this paper, a multi-label classification of the types of IDA, Vitamin B12, aplastic, and sickle cell anemia has been made by the machine learning problem transformation method which gives an idea of the type of anemia that is likely to occur due to the abnormal condition of CBC parameters.
Abstract: The CBC report is considered to be the most important report for assessing the overall health of the human body which is an important test for the diagnosis of diseases such as anemia, cancer, infections, vitamin, and mineral deficiencies. Anemia is a common health problem among people worldwide. Anemia is not a disease but a sign of a serious illness. Therefore, it can be prevented from serious diseases diagnosed at an earlier stage. The pattern of CBC parameters is found to be very complex. Therefore, a multi-label classification of the types of IDA, Vitamin B12, aplastic, and sickle cell anemia has been made by the machine learning problem transformation method which gives an idea of the type of anemia that is likely to occur due to the abnormal condition of CBC parameters. The use of the model can help predict anemia at an earlier stage. And serious diseases can be avoided. Ultimately, people can be saved from financial costs, kept mentally healthy, and concentration and regularity in teaching children can also be improved. This multi-label classification inspires the application of methods to classify these anemia types. Binary relevance, classifier chains, and label power set methods are used with different base classifications, and the results are analyzed. The results obtained by the SVM model based on the classifier chains method of multi-label classification have proved to be superior to other methods.
01 Jan 2012
TL;DR: An approach to estimate a discrete joint density online, that is, the algorithm is only provided the current example, its current estimate, and a limited amount of memory, is proposed.
Abstract: We propose an approach to estimate a discrete joint density online, that is, the algorithm is only provided the current example, its current estimate, and a limited amount of memory To design an online estimator for discrete densities, we use classifier chains to model dependencies among features Each classifier in the chain estimates the probability of one particular feature Because a single chain may not provide a reliable estimate, we also consider ensembles of classifier chains Our experiments on synthetic data show that the approach is feasible and the estimated densities approach the true, known distribution with increasing amounts of data
Posted Content
TL;DR: In this paper, the authors identify and discuss the main limitations of regressor chains, including an analysis of different base models, loss functions, explainability, and other desiderata of real-world applications.
Abstract: A large number and diversity of techniques have been offered in the literature in recent years for solving multi-label classification tasks, including classifier chains where predictions are cascaded to other models as additional features. The idea of extending this chaining methodology to multi-output regression has already been suggested and trialed: regressor chains. However, this has so-far been limited to greedy inference and has provided relatively poor results compared to individual models, and of limited applicability. In this paper we identify and discuss the main limitations, including an analysis of different base models, loss functions, explainability, and other desiderata of real-world applications. To overcome the identified limitations we study and develop methods for regressor chains. In particular we present a sequential Monte Carlo scheme in the framework of a probabilistic regressor chain, and we show it can be effective, flexible and useful in several types of data. We place regressor chains in context in general terms of multi-output learning with continuous outputs, and in doing this shed additional light on classifier chains.
Proceedings ArticleDOI
22 Sep 2017
TL;DR: This paper builds the deep belief networks (DBN) as a single-label classifier for each class, and extends the feature space for one class with the hidden layer information in the DBN built for other classes.
Abstract: In multi-label learning, each instance in the dataset is associated with a set of labels, and the correlations between different labels are important. The existing Classifier Chains transform the multi-label learning into a chain of binary classification and exploit label correlations by extending the feature space with the 0/1 label associations of all previous binary classifiers. In this paper, we exploit label correlations using the hidden layer information in deep networks. We build the deep belief networks(DBN) as a single-label classifier for each class, and extend the feature space for one class with the hidden layer information in the DBN built for other classes. Experiments on real-world multi-label learning problems shows that the DBN Chain structure is highly comparable to the existing method.

Network Information
Related Topics (5)
Deep learning
79.8K papers, 2.1M citations
77% related
Support vector machine
73.6K papers, 1.7M citations
77% related
Feature extraction
111.8K papers, 2.1M citations
76% related
Convolutional neural network
74.7K papers, 2M citations
76% related
Artificial neural network
207K papers, 4.5M citations
75% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202112
202018
201927
201812
201717
20166