Possibilistic Classifier Research Articles

Effects of Training Parameter Concept and Sample Size in Possibilistic c-Means Classifier for Pigeon Pea Specific Crop Mapping

This research work aims to study the effect of training parameter concept and sample size in the process of classification by using a fuzzy Possibilistic c-Means (PCM) approach for Pigeon Pea specific crop mapping. For specific class extraction, the “mean” of the training data is considered as a training parameter of the classification algorithm. In this study, we proposed an “Individual Sample as Mean” (ISM) approach where the individual training sample is accounted as a mean parameter for the fuzzy PCM classifier. In order to avoid the spectral overlap of target Pigeon pea crop with other crops in the study area, a temporal indices database was generated from Sentinel 2A/2B satellite images acquired during the 2019–2020 Pigeon Pea crop cycle. The spectral dimensionality of temporal data was reduced to extract the required bands to achieve maximum enhancement of the target crop class in the temporal data. Further, the training sample size was increased to study the heterogeneity within the class in the classified output. The proposed ISM approach delivered a higher mean membership difference (MMD) between the Pigeon Pea crop and the co-cultivated Cotton crop as compared to the conventional mean method. This indicated that a better separation was achieved between the target crop and the spectrally similar crop grown, that were cultivated in the same study area. When the sample size was gradually increased from 5 to 60, the MMD values within the Pigeon Pea test fields remained in the range 0.013–0.02, thereby implying that the proposed algorithm works better even with a small number of training samples. The heterogeneity was better handled using the proposed ISM approach since the variance obtained within Pigeon Pea field was only 0.008, as compared to that of 0.02 achieved using the conventional mean approach.

Handling non-linearity between classes using spectral and spatial information with kernel based modified possibilistic c-means classifier

In this research work, non-linearity in data has been handled by incorporating kernel with the Modified Possibilistic c-Means (MPCM) algorithm. Nine different types of kernel function have been proposed to classify nine different classes and have non-linearity among them. Gaussian has been identified as the best performing kernel at an optimized fuzzified value m = 1.5 with an overall accuracy 92.45%. The composite kernels have been generated with an aim of improvement of accuracy in comparison to single kernel. Further, role of spatial constraints has been analyzed by adding neighboring pixel information to handle the noise. It was observed that overall accuracy depends on the spatial parameter that has been included. Thus, local information having local similarity measure parameters (Sir)in the image produces highest accuracy compared to others. Moreover, the identified best kernel (Gaussian Kernel) has been then used for extraction of the burnt paddy fields in a different test site.

A novel possibilistic artificial immune-based classifier for course learning outcome enhancement

In this paper, we propose PAIRS3: a possibilistic classification approach based on artificial immune recognition system (AIRS) and the possibility theory. PAIRS3 is applied to address shortcomings in student attainment rates of course learning outcomes by predicting effective remedial actions through learning from assessment rubrics instances. For most of assessment rubric instances, it is difficult to determine the unique most effective remedial action to take. Consequently, each rubric instance will be labeled with uncertain remedial actions which are elicited from quality assurance experts. Elements from possibility theory are used to (1) model the uncertainty about the most effective remedial action labeling each rubric instance and (2) adapt several parts of the standard AIRS algorithm in order to address the uncertainty in class labels. The performance of the proposed method is evaluated against an academic, university level, assessment dataset that has been built progressively over multiple academic semesters. Despite the uncertainty related to the class labels in the dataset, PAIRS3 showed a good performance in terms of accuracy level (close to 75%). Also, when compared to existing state-of-the-art possibilistic classifiers such as PAIRS2, non-specificity possibilistic decision trees (NSPDT), and cluster-based possibilistic decision trees (Clust-PDT), PAIRS3 achieved better accuracy improvement ranging from 10% (in case of Clust-PDT) to 17% (in case of PAIRS2).

Fuzzy Clustering and Classification based Iris Recognition: A Medical Application

The Iris based authentication framework is basically a pattern recognition strategy that utilizes iris designs, which are factually unique. In this study, an efficient iris recognition system is developed with the help of Possibilistic Fuzzy C-Means Clustering (PFCM) and Fuzzy Logic classifier (FLC). The proposed methodology consists of four modules namely, pre-processing, segmentation, normalization and recognition. Initially, in the pre-processing module, the input images are adjusted to do further processing. Then, we segment the iris region from the input image with the help of PFCM. After that, the segmented image is normalized with the help of the Daugman Robber Sheet Model (DRS). Finally, the iris image is recognized with the help of FLC. The performance of the proposed methodology is analyzed in terms of different metrics namely, accuracy, false acceptance ratio (FAR) and false rejection ratio (FRR). Experimental results demonstrate, proposed PFCM+FLC method attains a better accuracy of 97.5%

A new possibilistic classifier for mixed categorical and numerical data based on a bi-module possibilistic estimation and the generalized minimum-based algorithm

A new possibilistic classifier for mixed categorical and numerical data based on a bi-module possibilistic estimation and the generalized minimum-based algorithm

One-Class Gaussian Process for Possibilistic Classification Using Imaging Spectroscopy

With the greater availability of imaging spectrometer data, vegetation species classification in the presence of outlier and ambiguous spectra is an increasingly important and poorly addressed problem. At large scales, assuming that all test spectra are from one of the training classes is unrealistic. An attractive resolution of these problems is the possibility theory, which is an axiomatic system, like probability theory, that represents uncertain labels of outliers and ambiguities more flexibly. In this letter, two popular probabilistic classification algorithms, namely, the support vector machine (SVM) with Platt scaling (SVM-Platt) and the Gaussian process (GP) classifier (GPC), are evaluated and compared to a novel one-class GP (OCGP) possibilistic classifier. OCGP, unlike one-class classification with GP, another GP-based one-class classifier, finds the hyperparameters automatically. Experiments were conducted with two data sets. The OCGP outperformed SVM-Platt and GPC when tested with outlier spectra.

Experimenting a discriminative possibilistic classifier with reweighting model for Arabic morphological disambiguation

In this paper, we experiment a discriminative possibilistic classifier with a reweighting model for morphological disambiguation of Arabic texts. The main idea is to provide a possibilistic classifier that acquires automatically disambiguation knowledge from vocalized corpora and tests on non-vocalized texts. Initially, we determine all the possible analyses of vocalized words using a morphological analyzer. The values of their morphological features are exploited to train the classifier. The testing phase consists in identifying the accurate class value (i.e., a morphological feature) using the features of the preceding and the following words. The appropriate class is the one having the greatest value of a possibilistic measure computed over the training set. To discriminate the effect of each feature, we add the weights of the training attributes to this measure. To assess this approach, we carry out experiments on a corpus of Arabic stories and on the Arabic Treebank. We present results concerning all the morphological features and we discern to which degree the discriminative approach improves disambiguation rates and extract the dependency relationships among the features. The results reveal the contribution of possibility theory for resolving ambiguities in real applications. We also compare the success rates in modern versus classical Arabic texts. Finally, we try to evaluate the impact of the lexical likelihood in morphological disambiguation.

Inference in possibilistic network classifiers under uncertain observations

Possibilistic networks, which are compact representations of possibility distributions, are powerful tools for representing and reasoning with uncertain and incomplete information in the framework of possibility theory. They are like Bayesian networks but lie on possibility theory to deal with uncertainty, imprecision and incompleteness. While classification is a very useful task in many real world applications, possibilistic network-based classification issues are not well investigated in general and possibilistic-based classification inference with uncertain observations in particular. In this paper, we address on one hand the theoretical foundations of inference in possibilistic classifiers under uncertain inputs and propose on the other hand a novel efficient algorithm for the inference in possibilistic network-based classification under uncertain observations. We start by studying and analyzing the counterpart of Jeffrey's rule in the framework of possibility theory. After that, we address the validity of Markov-blanket criterion in the context of possibilistic networks used for classification with uncertain inputs purposes. Finally, we propose a novel algorithm suitable for possibilistic classifiers with uncertain observations without assuming any independence relations between observations. This algorithm guarantees the same results as if classification were performed using the possibilistic counterpart of Jeffrey's rule. Classification is achieved in polynomial time if the target variable is binary. The basic idea of our algorithm is to only search for totally plausible class instances through a series of equivalent and polynomial transformations applied on the possibilistic classifier taking into account the uncertain observations.

Toward a computer study of the reliability of Arabic stories

AbstractThe Arabic storytelling methodology provides solutions to the problem of information reliability. The reliability of a story depends on the credibility of its narrators. To insure reliability verification, the narrators' names are explicitly cited at the head of the story, which constitute its chain of narrators. Stories were reported from a generation to another to insure the reliable transmission of historical knowledge. We present a set of tools based on the Arabic storytelling methodology. We start by presenting this methodology as a set of principles for information‐reliability assessment. Then, we detail an architecture designed to support the study of the reliability of Arabic stories. Indeed, we developed grammars for parsing Arabic full names and chains of narrators of Arabic stories. After that, an intelligent identity recognizer links names found in chains of narrators to the biographies of the corresponding persons. We model this step as a possibilistic information retrieval task. Finally, chains are analyzed through metadata available in biographies to help the user identify sources of unreliability. We propose to identify the class of reliability of a story with a possibilistic classifier. The achieved results in named entity and identity recognition were satisfactory and confirm to the targets set for the precision, recall, and F‐measure metrics. The developed tools also are reusable components that can be used to study the reliability of other types of Arabic texts.

Naïve possibilistic network classifiers

Naïve Bayesian network classifiers have proved their effectiveness to accomplish the classification task, even if they work under the strong assumption of independence of attributes in the context of the class node. However, as all of them are based on probability theory, they run into problems when they are faced with imperfection. This paper proposes a new approach of classification under the possibilistic framework with naïve classifiers. To output the naïve possibilistic network classifier, two procedures are studied namely the building phase, which deals with imperfect (imprecise/uncertain) dataset attributes and classes, and the classification phase, which is used to classify new instances that may be characterized by imperfect attributes. To improve the performance of our classifier, we propose two extensions namely selective naïve possibilistic classifier and semi-naïve possibilistic classifier. Experimental study has shown naïve Bayes style possibilistic classifier, and is efficient in the imperfect case.