Attribute Selection Techniques Research Articles

An Approach to Detect Credit Card Frauds using Attribute Selection and Ensemble Techniques

An Approach to Detect Credit Card Frauds using Attribute Selection and Ensemble Techniques

Tolerance-based intuitionistic fuzzy-rough set approach for attribute reduction

Due to technological advancement and the explosive growth of electrically stored information, automated methods are required to aid users in maintaining and processing this huge amount of information. Experts, as well as machine learning processes on large volumes of data, are the main sources of knowledge. Knowledge extraction is an important step in framing expert and intelligent systems. However, the knowledge extraction phase is very slow or even impossible due to noise and large size of data. To enhance the productivity of machine learning algorithms, feature selection or attribute reduction plays a key role in the selection of relevant and non-redundant features to improve the performance of classifiers and interpretability of data. Many areas like machine learning, image processing, data mining, natural language processing and Bioinformatics, etc., which have high relevancy to expert and intelligent systems, are applications of feature selection.Rough set theory has been successfully applied for attribute reduction, but this theory is inadequate in the case of attribute reduction of real-valued data set as it may lose some information during the discretization process. Fuzzy and rough set theories have been combined and various attribute selection techniques were proposed, which can easily handle the real-valued data. An intuitionistic fuzzy set possesses a strong ability to represent information and better describing the uncertainty when compared to the classical fuzzy set theory as it considers positive, negative and hesitancy degree simultaneously for an object to belong to a set. This paper proposes a novel mechanism of attribute selection using tolerance-based intuitionistic fuzzy rough set theory. For this, we present tolerance-based intuitionistic fuzzy lower and upper approximations and formulate a degree of dependency of decision features over the set of conditional features. Moreover, the basic results on lower and upper approximations based on rough sets are extended for intuitionistic fuzzy rough sets and analogous results are established. In the end, the proposed algorithm is applied to an example data set and the comparison between tolerance-based fuzzy rough and intuitionistic fuzzy rough sets approaches for feature selection is presented. The proposed concept is found to be better performing in the form of selected attributes.

Sample-Based Attribute Selective A$n$ DE for Large Data

More and more applications have come with large data sets in the past decade. However, existing algorithms cannot guarantee to scale well on large data. Averaged n -Dependence Estimators (A n DE) allows for flexible learning from out-of-core data, by varying the value of $n$ (number of super parents). Hence, A n DE is especially appropriate for large data learning. In this paper, we propose a sample-based attribute selection technique for A n DE. It needs one more pass through the training data, in which a multitude of approximate A n DE models are built and efficiently assessed by leave-one-out cross validation. The use of a sample reduces the training time. Experiments on 15 large data sets demonstrate that the proposed technique significantly reduces A n DE's error at the cost of a modest increase in training time. This efficient and scalable out-of-core approach delivers superior or comparable performance to typical in-core Bayesian network classifiers.

Attribute Selection via a Novel Interval Based Evaluation Algorithm: Applied on Real life data sets

Real life problems handled by machine learning deals with various forms of values in the data set attributes, like the continuous and discrete form. Discretization is an important step in the pre-processing stage as most of the attribute selection techniques assume the discreetness of the input values. This step could change the internal structure of the input attribute values with respect to the classification problem, and thus the quality of this step directly impact the quality of the selected features. This work discusses the problems existing in the current discretization techniques and proposes an attribute evaluation and selection technique to avoid these problems. Attributes are evaluated in its continuous form directly without biasing its internal structure and enhances the computational complexity by eliminating the discretization step. The basic insight of the proposed approach relies on the inverse relationship between class label distribution overlap and the relative information content of a given attribute. In order to estimate the validity of this assumption, a series of data sets were examined using several standard approaches including our own implementation, and the approaches ranked with respect to the overall classification accuracy. The results, at least with respect to the testing data sets deployed in this study, indicate that the proposed approach outperformed other methods selected for evaluation in this study. These results will be examined over a wider range of continuous attribute data sets from nonmedical domains in order to investigate the robustness of these results.

An Empirical Study on Different Ranking Methods for Effective Data Classification

Ranking is the attribute selection technique used in the pre-processing phase to emphasize the most relevant attributes which allow models of classification simpler and easy to understand. It is a very important and a central task for information retrieval, such as web search engines, recommendation systems, and advertisement systems. A comparison between eight ranking methods was conducted. Ten different learning algorithms (NaiveBayes, J48, SMO, JRIP, Decision table, RandomForest, Multilayerperceptron, Kstar) were used to test the accuracy. The ranking methods with different supervised learning algorithms give different results for balanced accuracy. It was shown the selection of ranking methods could be important for classification accuracy.

Reliable context-aware multi-attribute continuous authentication framework for secure energy utilization management in smart homes

In smart homes, users remotely manage resource utilization tasks and context-aware services using portable devices and mobile communication technologies. Reliability of automated energy consumption management relies upon context-aware continuous authentications of users in executing time-critical tasks. In particular, the contexts of mobility of users and the critical nature of the task are important. Continuous authentication is a robust technique to ensure validity of the authenticity of users over time. Existing continuous authentication techniques do not use the contextual information and dynamic user behavioral characteristics for authentications. We propose a novel context-aware multi-attribute continuous authentication model for secure energy utilization management in smart homes. We use location and the critical nature of the tasks as the contextual information as supporting information for selecting the authentication attributes. We propose novel location and task profiles as context specification metrics and a novel relative-importance based attribute selection technique based on N-model. The usefulness of the proposed solution is validated using real-world data sets. Furthermore, the reliability of the proposed risk based resource management model is analysed as a constraint model using linear temporal logic. Based on the experimental results, this research provides meaningful insights to use pragmatic approaches with security and reliability assurances for resource management applications in smart homes.

Automatic welding detection by an intelligent tool pipe inspection

This work provide a model based on machine learning techniques in welds recognition, based on signals obtained through in-line inspection tool called “smart pig” in Oil and Gas pipelines. The model uses a signal noise reduction phase by means of pre-processing algorithms and attribute-selection techniques. The noise reduction techniques were selected after a literature review and testing with survey data. Subsequently, the model was trained using recognition and classification algorithms, specifically artificial neural networks and support vector machines. Finally, the trained model was validated with different data sets and the performance was measured with cross validation and ROC analysis. The results show that is possible to identify welding automatically with an efficiency between 90 and 98 percent.

Towards Improvement of Analogy-Based Software Development Effort Estimation: A Review

In this paper a systematic review is conducted to investigate the structure, components, techniques, evaluation procedure, and comparison scope related to prior ABE-based studies. The undeniable role of accurate development effort estimation in the success of software project management has attracted the attention of researchers over the past few years. Among various algorithmic and non-algorithmic estimation methods, analogy based estimation (ABE) is a widely accepted method due to its simplicity and estimation capability. This paper investigates the improvement process of ABE method during 2000 to 2012. Six research questions are defined to be addressed through evaluation of prior ABE-based studies. The review domain includes 24 papers selected through a tough filtration process. The results show that improvement of ABE can be performed through adjustment, grey theory, attribute weighting and attribute selection techniques. Moreover, ABE configurations can significantly affect the results.

Exploring the Effectiveness of Seller Reputation Mechanism Using Online Sales Data

This paper attempts to explore the effectiveness of the seller reputation mechanism by an empirical study using online sales data collected from TaoBao.com. A comparison analysis of seller reputation metrics of TaoBao, Amazon, and jd are carried out before the selection of the seller reputation metrics. The seller reputation metrics of small appliances are used as the input for the study considering the quality homogeneity among different sellers of the market, and the sales performance is measured by the sales amount of the recent month. The univariate analysis are performed to find out the effect of different seller reputation metrics on the sales performance, and the attribute selection technique is then applied to reveal the most significant factors contributing to the sales performance. The result indicates the significance of the user subjective assessment on the sales performance.

Improving Efficiency of Classification using PCA and Apriori based Attribute Selection Technique

The aim of this study is to select significant features that contribute for accuracy in classification. Data mining is a field where we find lots of data which can be useful or useless in any form available in Data Warehouse. Implementing classification on these huge, uneven, useless data sets with large number of features is just a waste of time degrading the efficiency of classification algorithms and hence the results are not much accurate. Hence we propose a system in which we first use PCA (Principal Component Analysis) for selection of the attributes on which we perform Classification using Bayes theorem, Multi-Layer Perceptron, Decision tree J48 which indeed has given us better result than that of performing Classification on the huge complete data sets with all the attributes. Also association rule mining using traditional Apriori algorithm is experimented to find out sub set of features related to class label. The experiments are conducted using WEKA 3.6.0 Tool.

Adaptive Approach of Fault Prediction in Software Modules by using Discriminative and Generative Model of Machine Learning

Software quality assurance is the most important activity during the development of software. Defective software modules may increase costs and decrease customer satisfaction. Hence, effective defect prediction models or techniques are very important in order to deliver efficient software. In this research different machine learning algorithms are used to predict three main prediction performance measures i.e. precision, recall and f-measure. The accuracy of the software modules is being calculated. Different classifiers are also used in order to predict the values of these measures by using important attributes only. The results obtained after applying both the techniques i.e. attribute selection and without attribute selection, on all the datasets, are then analysed and best predicted results are chosen in order to predict the correct values of prediction performance measures. The accuracy of some software modules can be improved to 91.16%, recall and precision to 1 after using attribute selection techniques in CM1 dataset. In PC1 dataset the accuracy has been improved to 93.778%. General Terms Defect Prediction Models, Faulty Modules, Accuracy, Data Mining.

An Empirical Investigation of Attribute Selection Techniques based on Shannon, Rényi and Tsallis Entropies for Network Intrusion Detection

Intrusion Detection Systems of computer network perform their detection capabilit ies by monitoring a set of attributes from network traffic. Since some attributes may be irrelevant, redundant or even noisy, their usage can decrease the intrusion detection efficiency as well as increase the set of attributes. In this context, selecting optimal attributes is a difficult task considering that the set of all attributes can assume a huge variety of data formats (for examp le: symbol set, e.g. binary, alphanumeric, real number, etc., types, length, among others). In this work, it is presented an empirical investigation of attribute selection techniques based on Shannon, Renyi and Tsallis entropies in order to obtain optimal attribute subsets that increase the detection capability of classifying network traffic as either normal or suspicious. Simu lation experiments have been carried out and the obtained results show that when Renyi or Tsallis entropy is applied the number of attributes and the processing time are reduced and, in addition, the classificat ion efficiency is increased.

An Empirical Investigation of Filter Attribute Selection Techniques for High-Speed Network Traffic Flow Classification

Attribute selection is an important methodology for data mining problems. Removing irrelevant and redundant attributes from original data set can greatly simplify building classifier models. In this paper, we consider applying attribute selection techniques to network traffic flow classification and conduct experiments using the actual network data collected from the Internet of China. The results show that building with an appropriate attribute selection method can simplify the network traffic classifier while achieving satisfactory classification accuracy.

Lung Cancer Survival Prediction using Ensemble Data Mining on Seer Data

We analyze the lung cancer data available from the SEER program with the aim of developing accurate survival prediction models for lung cancer. Carefully designed preprocessing steps resulted in removal/modification/splitting of several attributes, and 2 of the 11 derived attributes were found to have significant predictive power. Several supervised classification methods were used on the preprocessed data along with various data mining optimizations and validations. In our experiments, ensemble voting of five decision tree based classifiers and meta-classifiers was found to result in the best prediction performance in terms of accuracy and area under the ROC curve. We have developed an on-line lung cancer outcome calculator for estimating the risk of mortality after 6 months, 9 months, 1 year, 2 year and 5 years of diagnosis, for which a smaller non-redundant subset of 13 attributes was carefully selected using attribute selection techniques, while trying to retain the predictive power of the original set of attributes. Further, ensemble voting models were also created for predicting conditional survival outcome for lung cancer (estimating risk of mortality after 5 years of diagnosis, given that the patient has already survived for a period of time), and included in the calculator. The on-line lung cancer outcome calculator developed as a result of this study is available at http://info.eecs.northwestern.edu:8080/LungCancerOutcomeCalculator/.

Irrelevant attributes and imbalanced classes in multi-label text-categorization domains

An interesting issue in machine learning is induction in multi-label domains where each example can be labeled with two or more classes at the same time. In a work focusing on text categorization, we followed the most commonly used approach and induced a binary classifier for each class. Analyzing the results, we noticed that performance had been impaired by two factors. First, in text domains, each class is characterized by a different set of attributes; an appropriate attribute-selection technique thus has to be applied separately to each of them. Second, the individual classes often have to be induced from imbalanced training sets, a circumstance we addressed here by majority-class undersampling. The paper provides details of the induction system and reports the results of systematic experimentation.

Data Mining Applied to Identification of Harmonic Sources in Residential Consumers

This work proposes a method based on both preprocessing and data mining with the objective of identify harmonic current sources in residential consumers. In addition, this methodology can also be applied to identify linear and nonlinear loads. It should be emphasized that the entire database was obtained through laboratory essays, i.e., real data were acquired from residential loads. Thus, the residential system created in laboratory was fed by a configurable power source and in its output were placed the loads and the power quality analyzers (all measurements were stored in a microcomputer). So, the data were submitted to pre-processing, which was based on attribute selection techniques in order to minimize the complexity in identifying the loads. A newer database was generated maintaining only the attributes selected, thus, Artificial Neural Networks were trained to realized the identification of loads. In order to validate the methodology proposed, the loads were fed both under ideal conditions (without harmonics), but also by harmonic voltages within limits pre-established. These limits are in accordance with IEEE Std. 519-1992 and PRODIST (procedures to delivery energy employed by Brazilian's utilities). The results obtained seek to validate the methodology proposed and furnish a method that can serve as alternative to conventional methods.

The application of a new attribute selection technique to the forecasting of housing value using dependence modelling

This article introduces the J-score, a heuristic feature selection technique capable of selecting a useful subset of attributes from a dataset of potential inputs. The utility of the J-score is demonstrated through its application to a dataset containing historical information that may influence the house price index in the United Kingdom. After selecting a subset of features deemed appropriate by the J-score, a predictive model is trained using an artificial neural network. This model is then tested and the results compared with those from an alternative model, built using a subset of features suggested by the Gamma test, a non-linear analysis algorithm that is described. Other control subsets are also used for the assessment of the J-score model quality. The predictive accuracy of the J-score model relative to other models provides evidence that the J-score has good potential for further practical use in a variety of problems in the feature selection domain.

Benchmarking attribute selection techniques for discrete class data mining

Data engineering is generally considered to be a central issue in the development of data mining applications. The success of many learning schemes, in their attempts to construct models of data, hinges on the reliable identification of a small set of highly predictive attributes. The inclusion of irrelevant, redundant, and noisy attributes in the model building process phase can result in poor predictive performance and increased computation. Attribute selection generally involves a combination of search and attribute utility estimation plus evaluation with respect to specific learning schemes. This leads to a large number of possible permutations and has led to a situation where very few benchmark studies have been conducted. This paper presents a benchmark comparison of several attribute selection methods for supervised classification. All the methods produce an attribute ranking, a useful devise for isolating the individual merit of an attribute. Attribute selection is achieved by cross-validating the attribute rankings with respect to a classification learner to find the best attributes. Results are reported for a selection of standard data sets and two diverse learning schemes C4.5 and naive Bayes.