A self learning rough fuzzy neural network classifier for mining temporal patterns

Sethukkarasi, R.; Keerthika, U.; Kannan, A.

doi:10.1145/2345396.2345415

Cited by 6 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Definition 3: Let A = <U, A, d> be a decision system, B ⊆ A, X ⊆ U and [x]B denote the equivalence class of IA(B). The B-lower approximation and B-upper approximation of X, denoted by bX and BX respectively, are defined by bX = {x | [x] B ⊆ X} and BX = {x | [x] B ∩ X ≠ ∅} [13], [14].…”

Section: Related Terms and Definitionsmentioning

confidence: 99%

Rough Set Theory Based Reasoning of Learning Style in e-Learning

Rana¹

2014

IJEEEE

View full text Add to dashboard Cite

The growth of e-learning is expanding tremendously. In this context, LMS is software for handling various management related activities in respect of learning and its delivery in online mode. The proposed system provides the learning content according to learner's learning style using the extracted rule. Rough sets may be seen as an emerging tool & technique for extracting knowledge from a large set of data. Rough set theory is particularly useful for discovering relationships and used to deal with imprecise or incomplete data. This is a case study in which we suggest an effective way to extract rule which can decide learner's learning style in e-learning environments through RSES software. In this study, we used concept of reducts to extract appropriate knowledge from large datasets and calculate confidence factor for conflicting rules. Rough Set Theory in e-learning environment can bring immense potential and will make E-learning procedure more interesting, decision friendly, and user friendly. The proposed system will be able to increase efficiency of learning as providing learning contents based on learner's style.

show abstract

Section: Related Terms and Definitionsmentioning

confidence: 99%

Rough Set Theory Based Reasoning of Learning Style in e-Learning

Rana¹

2014

IJEEEE

View full text Add to dashboard Cite

show abstract

“…Temporal patterns can be mined by applying fuzzy neural networks. Lower approximations can be derived by implementing hypothesis and fuzzy decision tables [17]. A novel approach was proposed for classification based on bijective soft sets.…”

Section: Literature Surveymentioning

confidence: 99%

A Comparative Analysis of Classification Techniques on Medical Data Sets

Mittal¹

2014

IJRET

View full text Add to dashboard Cite

Classification is the preliminary stage of data mining which is used to categorize the dataset in smaller groups where each group contains the similar data items. The classification basically deals with two main parameters; one is the number of classes and another is the criteria for deciding the class members. Different recognition algorithms also use the classification process as an initial stage to perk up the efficiency and the accuracy. The accuracy of the classification algorithm also decides the effectiveness of its use in other mining applications. The present work is about to analyze the effectiveness of the most popular classification techniques. In this paper, the analysis has been performed for five different classification algorithms in terms of accuracy, kappa statistics, execution time, mean absolute error under three datasets, collected from medical domain. The work has been implemented in WEKA environment and obtained results show that SVM is the most robust classification method and KNN is the least effective classifier for medical data sets.

show abstract

“…Neural Networks traditionally used to refer to networks. It is also referred as circuit of biological neurons [9]. In Neural Networks a hidden layer is used between the two extremes i.e.…”

Section: Neural Networkmentioning

confidence: 99%

“…In Neural Networks a hidden layer is used between the two extremes i.e. input layer and output layer to create a model [9]. The artificial networks can be utilized for predictive modelling, adaptive control etc.…”

Section: Neural Networkmentioning

confidence: 99%

Large Scale Hierarchical Classification

Khalique,

Hasnani

2013

JISR-C

View full text Add to dashboard Cite

This study elucidates various algorithms used for document or text classification challenge. A sample data is used in this study on which various algorithms like Support Vector Machines (SVM), Naïve Bayes, Neural Networks and K-Nearest Neighbor are used in order to analyze their performances and accuracies. This study tries to identify the limitations and strength of these algorithms on the given sample data that how optimally they can perform classification. Different validations are used in this study to examine the accuracies regarding the classification can be identified. Validations include Split-Validation, X-Validation and Bootstrapping. Different ways and methods are discussed through which classification is made possible in large hierarchy. Finally this study concludes on the basis of results obtained that which machine learning technique or classifier performed excellent on the provided sample data set and achieved higher accuracy as compared to others.

show abstract

A self learning rough fuzzy neural network classifier for mining temporal patterns

Cited by 6 publications

References 12 publications

Rough Set Theory Based Reasoning of Learning Style in e-Learning

Rough Set Theory Based Reasoning of Learning Style in e-Learning

A Comparative Analysis of Classification Techniques on Medical Data Sets

Large Scale Hierarchical Classification

Contact Info

Product

Resources

About