Rough Set Reduction Research Articles

Gene Expression Programming for Attribution Reduction in Rough Set

This paper presents gene expression programming for attribution reduction in rough set (GEP-ARRS), which designs a new GEP code to convert attribution reduction into an expression tree and a new fitness function. Meanwhile, to solve optimal reduction, GEP ARRS implements a dynamic population creation strategy to reduce the gene length of GEP to accelerate solution efficiency of GEP. Through extensive experiments on mass or high-dimensional data sets, it is shown that GEP-ARRS is apparently more advantageous in terms of speed and quality in contrast with traditional attribution reduction algorithms on intelligence computing.

Process Expert System in NC Camshaft Grinding on the Basis of Rough Set and Case-based Reasoning

For the difficult issues of process selection about NC camshaft grinding,on the basis of synthesizing the advantages of rough set (RS) theory and case-based reasoning (CBR),a new RS-CBR process expert system is put forward. In the system,the discrete algorithm and its reduction of RS is used to carry out automatic calculation of process feature attribute weights; the CBR is used to calculate the similarity of process cases. A series of experiments are accomplished by using uniform design principle on CNC8312A NC camshaft grinder,and several groups of data are obtained to establish process case database. On this basis,the RS-CBR model of NC camshaft grinding is established to match grinding process intelligently. A satisfied result is obtained by applying the matched process case to actual production.

Neighborhood Rough Set Reduction-Based Gene Selection and Prioritization for Gene Expression Profile Analysis and Molecular Cancer Classification

Selection of reliable cancer biomarkers is crucial for gene expression profile-based precise diagnosis of cancer type and successful treatment. However, current studies are confronted with overfitting and dimensionality curse in tumor classification and false positives in the identification of cancer biomarkers. Here, we developed a novel gene-ranking method based on neighborhood rough set reduction for molecular cancer classification based on gene expression profile. Comparison with other methods such as PAM, ClaNC, Kruskal-Wallis rank sum test, and Relief-F, our method shows that only few top-ranked genes could achieve higher tumor classification accuracy. Moreover, although the selected genes are not typical of known oncogenes, they are found to play a crucial role in the occurrence of tumor through searching the scientific literature and analyzing protein interaction partners, which may be used as candidate cancer biomarkers.

Intrusion Detection Method Using Protocol Classification and Rough

In order to improve the efficiency of support vector intrusion detection, we first do protocol Classification for the intrusion data, then refine its characteristic by rough set reduction. By using these procedures, we propose an intrusion detection method using protocol classification and rough set based support vector machine. The method is divided into training and testing processes. In the process of training, we first do protocol classification for the training data, and then do rough set refinement. The refined characteristics are stored as the pre-defined process, and finally the usage of support vector machine for data reduction training, the training model will be stored in accordance with the agreement. In the testing process, the data is classified according to protocol classification and then start the characteristics reduction procedure according to protocol classification. Finally, make a decision using the Support Vector Machines that corresponding to the agreement. The experimental results based on KDDCUP'99 data show that the method is the method is faster and the detection accuracy is comparable compared with the SVM without using protocol classification and using all characteristic.

Control approach to rough set reduction

Rough Set reduction is a typical iterative process; however, the user cannot give extra controls and preferences during the consecutively iterative process. In this paper, we propose a novel approach to Rough Set reduction by using control science viewpoint. In this model, information system is regarded as controlled plant, user’s preference about attributes is regarded as control objective, and the iterative algorithm designing process is regarded as control law designing. We have investigated the properties of Rough Set reduction based on control approach, and have designed the control system based on the properties, where single attribute set and user specified attributes are all used as core attributes to control a pruning process, and other core attributes worked out by previous steps are also used, iteratively. Such that it forms a dynamic closed-loop control by which the user can give much more interactivities. We have also implemented the experimental platform, and the experimental results show that the proposed approach is efficient and effective.

Study on the quantitative structure-activity relationship of C-10 substituted artemisinin (QHS)’s derivatives using rough set theory

The structure-activity relationship study of C-10 substituted artemisinin (QHS) derivatives that are used as antimalarial was performed with the RS (rough sets) method. An RS process is a concise nonlinear process, and it has broad application foreground in the data mining of nonlinear life courses. In this work, initially the parameters of C-10 substituted QHS’s derivatives were computed with the quantum chemistry method, and the information table was constructed from the parameters (condition attributes) and biological activity (decision attributes). Based on the analysis of rough set theory, the core and reduction of attributes sets were obtained. Then the decision rules were extracted and the structure-activity relationship was analyzed. As a nonlinear system, RS theory can extract the special relation in the database. It has the advantage of being nonlinear over multiple linear regression (MLR), principal component analysis (PCA), partial least square (PLS), etc., and the advantage of obtaining results with unambiguous physical meanings over artificial neuron networks (ANNs), etc. The result obtained in this study is instructive to the study of pharmacodynamics, resistance mechanism of QHS and development of QHS’s derivatives.

Generalization rough set theory and real-valued attributes reduction

Considering that the classical rough set theory can only process the discrete data,the degree of general importance of an attribute and attribute subsets was presented.And then a generalization rough set theory was proposed based on the general near neighborhood relation.The theory partitioned the universe into the tolerant modules and formed lower approximation and upper approximation of the set under general near neighborhood relationship which avoided the discretization in Pawlak's rough set.Furthermore,the definition of attribute reduction in generalization rough set and its greedy algorithm were proposed.Finally,results of some examples show the correctness and validity of this method.

Rough Sets Data Analysis in Knowledge Discovery: A Case of Kuwaiti Diabetic Children Patients

The main goal of this study is to investigate the relationship between psychosocial variables and diabetic children patients and to obtain a classifier function with which it was possible to classify the patients on the basis of assessed adherence level. The rough set theory is used to identify the most important attributes and to induce decision rules from 302 samples of Kuwaiti diabetic children patients aged 7–13 years old. To increase the efficiency of the classification process, rough sets with Boolean reasoning discretization algorithm is introduced to discretize the data, then the rough set reduction technique is applied to find all reducts of the data which contains the minimal subset of attributes that are associated with a class label for classification. Finally, the rough sets dependency rules are generated directly from all generated reducts. Rough confusion matrix is used to evaluate the performance of the predicted reducts and classes. A comparison between the obtained results using rough sets with decision tree, neural networks, and statistical discriminate analysis classifier algorithms has been made. Rough sets show a higher overall accuracy rates and generate more compact rules.

An Integrated Neural Classifier for Stream Turbine Damage Identification Based on PSO

To improve the accuracy and overcome the flaws of single neural network, an integrated neural classifier for stream turbine vibration fault identification is proposed based on particle swarm optimization (PSO) in the paper. The method firstly establishes diagnosis decision table of stream turbines from fault sources to fault symptoms based on wavelet package decomposition technique to faults wave-shape. Then the discrete decision table is acquired by quantifying attribute values in decision table using information entropy, a simplified decision table then is generated by rough set reduction. Based on it, several neural networks are applied to identify steam turbine faults at the same time, and their results are integrated with PSO-based. Both simulation and trial in stream turbine damage identification indicate that the proposed method has higher identification rate and shorter training time as well as excellent generalized ability, and is an ideal pattern classifier.

Content-Based Image Classification and Retrieval

Advances in data storage and image acquisition technologies have enabled the creation of large image datasets. Thus, it is necessary to develop appropriate information systems to efficiently manage these datasets. Image classification and retrieval is one of the most important services that must be supported by such systems. The most common approach used is content-based image retrieval (CBIR) systems. This paper presents a new application of rough sets to feature reduction, classification, and retrieval for image databases in the framework of content-based image retrieval systems. The suggested approach combines image texture features with color features to form a powerful discriminating feature vector for each image. Texture features are extracted, represented, and normalized in an attribute vector, followed by a generation of rough set dependency rules from the real value attribute vector. The rough set reduction technique is applied to find all reducts with the minimal subset of attributes associated with a class label for classification

The Diagnostic Rules of Peripheral Lung Cancer Preliminary Study Based on Data Mining Technique

Objective To discuss the clinical and imaging diagnostic rules of peripheral lung cancer by data mining technique, and to explore new ideas in the diagnosis of peripheral lung cancer, and to obtain early-stage technology and knowledge support of computer-aided detecting (CAD). Methods 58 cases of peripheral lung cancer confirmed by clinical pathology were collected. The data were imported into the database after the standardization of the clinical and CT findings attributes were identified. The data was studied comparatively based on Association Rules (AR) of the knowledge discovery process and the Rough Set (RS) reduction algorithm and Genetic Algorithm(GA) of the generic data analysis tool (ROSETTA), respectively. Results The genetic classification algorithm of ROSETTA generates 5000 or so diagnosis rules. The RS reduction algorithm of Johnson's Algorithm generates 51 diagnosis rules and the AR algorithm generates 123 diagnosis rules. Three data mining methods basically consider gender, age, cough, location, lobulation sign, shape, ground-glass density attributes as the main basis for the diagnosis of peripheral lung cancer. Conclusion These diagnosis rules for peripheral lung cancer with three data mining technology is same as clinical diagnostic rules, and these rules also can be used to build the knowledge base of expert system. This study demonstrated the potential values of data mining technology in clinical imaging diagnosis and differential diagnosis.

Rough set and fuzzy wavelet neural network integrated with least square weighted fusion algorithm based fault diagnosis research for power transformers

In this paper, a rough set (RS) and fuzzy wavelet neural network (FWNN), integrated with least square weighted fusion algorithm based fault diagnosis for power transformers, using dissolved gas analysis (DGA) is proposed. This approach takes advantage of the knowledge reduction ability of rough set and good classified diagnosis ability of FWNN, integrated with least square (LS) weighted fusion algorithm. The rough set is used as a front of FWNN, integrated with LS weighted fusion algorithm to simplify the input of FWNN and mine the rules whose “confidence” and “support” satisfy a preset criteria. The mined rules are used as a diagnosis knowledge base to offer fault diagnosis service for power transformers. FWNN, integrated with LS weighted fusion algorithm, is used to diagnose the case that cannot be diagnosed by mined rules by rough set. The FWNN input is simplified by rough set reduction, and its learning rate is improved greatly. FWNN, integrated with LS weighted fusion algorithm, on one side, can much better improve the diagnosis accuracy, when the output vector of single FWNN has the similar element. On the other hand, its diagnosis accuracy cannot be limited by the neural network hidden layer number and correlated training parameter. The mechanism has good classified diagnosis ability. The advantages and effectiveness of this method are verified by testing.

The application of rough sets in SAR analysis of N1-site substituted fluoroquinolones

The 3 dimension structure–activity relationships (3D-SAR) for N1-site substituted fluoroquinolones that used as antibiotics were performed with RS (rough sets) method. The process of RS is a concise nonlinear process, it has broad application foreground in the data mining of nonlinear life course. In this paper, initially the parameters of N1-site substituted quinolones were computed with the semi-empirical method: AM1 (Austin model) and MNDO3 (modified neglect diatomic overlap), and the information table is composed of the parameters (condition attributes) and biology activity (decision attributes). According to the analysis of rough sets method, the core and reduction of attributes set were obtained, then the decision rules were extracted. The results indicate that LUMO, A5, A3 and dipole, etc. have the great contribution to the activity of N1-site substituted fluoroquinolones. Integrating the related biological research of fluoroquinolones resistance, the binary hydrogen bond mechanism of fluoroquinolones is brought forward. It implies that fluoroquinolones realize their function as electron donors as well as electron acceptors in its function process, and the process is finished by the formation of two hydrogen bonds (6-site F and 3-site OH). The mutation of bacteria makes it hard to form hydrogen bonds, then cause the fluoroquinolones resistance. The result also indicates that moderate dipole and ΔHf are helpful to fluoroquinolones to be absorbed by the human body and act on bacteria. As a nonlinear system, RS theory can extract the special relation in the database, it has nonlinear character compared with PCA (Principal Component Analysis), PLS (Partial Least Square), etc., and the result has unambiguous physical meaning compared with ANN (Artificial Neuron Network), etc. The result is very succinct and pointed, it is instructive to the study of pharmacody function process, resistance mechanism of fluoroquinolones and development of new fluoroquinolones.

Reducing the Memory Size of a Fuzzy Case-Based Reasoning System Applying Rough Set Techniques

Early work on case-based reasoning (CBR) reported in the literature shows the importance of soft computing techniques applied to different stages of the classical four-step CBR life cycle. This correspondence proposes a reduction technique based on rough sets theory capable of minimizing the case memory by analyzing the contribution of each case feature. Inspired by the application of the minimum description length principle, the method uses the granularity of the original data to compute the relevance of each attribute. The rough feature weighting and selection method is applied as a preprocessing step prior to the generation of a fuzzy rule system, which is employed in the revision phase of the proposed CBR system. Experiments using real oceanographic data show that the rough sets reduction method maintains the accuracy of the employed fuzzy rules, while reducing the computational effort needed in its generation and increasing the explanatory strength of the fuzzy rules

Reduction of rough set attribute based on immune clone selection

A novel attribute reduction approach of rough set based on immune clone selection is proposed. In this method, the approximation quality and attribute set were adopted as evolution object and antibody, respectively. On the basis of the inherent distribution within the immune response, the global optimization of the antibody was realized through parallel local optimization. Moreover, the diversity of the antibody population was maintained with the affinity maturation and renewal of the antibody. Thus, the stable multi-optimal solutions can be preserved. In addition, the machinery fault data were analyzed by this method, and the attribute reduction sets were obtained further to satisfy the demand of feature selection in machinery diagnosis.

Feature selection based on rough sets and particle swarm optimization

We propose a new feature selection strategy based on rough sets and particle swarm optimization (PSO). Rough sets have been used as a feature selection method with much success, but current hill-climbing rough set approaches to feature selection are inadequate at finding optimal reductions as no perfect heuristic can guarantee optimality. On the other hand, complete searches are not feasible for even medium-sized datasets. So, stochastic approaches provide a promising feature selection mechanism. Like Genetic Algorithms, PSO is a new evolutionary computation technique, in which each potential solution is seen as a particle with a certain velocity flying through the problem space. The Particle Swarms find optimal regions of the complex search space through the interaction of individuals in the population. PSO is attractive for feature selection in that particle swarms will discover best feature combinations as they fly within the subset space. Compared with GAs, PSO does not need complex operators such as crossover and mutation, it requires only primitive and simple mathematical operators, and is computationally inexpensive in terms of both memory and runtime. Experimentation is carried out, using UCI data, which compares the proposed algorithm with a GA-based approach and other deterministic rough set reduction algorithms. The results show that PSO is efficient for rough set-based feature selection.

Rough set feature selection and rule induction for prediction of malignancy degree in brain glioma

The degree of malignancy in brain glioma is assessed based on magnetic resonance imaging (MRI) findings and clinical data before operation. These data contain irrelevant features, while uncertainties and missing values also exist. Rough set theory can deal with vagueness and uncertainty in data analysis, and can efficiently remove redundant information. In this paper, a rough set method is applied to predict the degree of malignancy. As feature selection can improve the classification accuracy effectively, rough set feature selection algorithms are employed to select features. The selected feature subsets are used to generate decision rules for the classification task. A rough set attribute reduction algorithm that employs a search method based on particle swarm optimization (PSO) is proposed in this paper and compared with other rough set reduction algorithms. Experimental results show that reducts found by the proposed algorithm are more efficient and can generate decision rules with better classification performance. The rough set rule-based method can achieve higher classification accuracy than other intelligent analysis methods such as neural networks, decision trees and a fuzzy rule extraction algorithm based on Fuzzy Min–Max Neural Networks (FRE-FMMNN). Moreover, the decision rules induced by rough set rule induction algorithm can reveal regular and interpretable patterns of the relations between glioma MRI features and the degree of malignancy, which are helpful for medical experts.

On the relation between rough set reducts and jumping emerging patterns

This paper presents the relations between rough set reducts and jumping emerging patterns. Observations are introduced formally and supported by brief examples. Furthermore, we propose practical applications of these observations to the minimal reduct problem and to testing whether a given attribute set is differentiating. We believe that our study can be expanded so as to include other types of reducts and emerging patterns.

Rough sets and ordinal reducts

Rough set theory has been successfully applied in selecting attributes to improve the effectiveness in deriving decision trees/rules for decisions and classification problems. When decisions involve ordinal classes, the rough set reduction process should try to preserve the order relation generated by the decision classes. Previous works on rough sets when applied to ordinal decision systems still focus on preserving the information relating to the decision classes and not the underlying order relation. In this paper, we propose a new way of evaluating and finding reducts involving ordinal decision classes which focus on the order generated by the ordinal decision classes.

Rough set approach for attribute reduction and rule generation: A case of patients with suspected breast cancer

AbstractRough set theory is a relatively new intelligent technique used in the discovery of data dependencies; it evaluates the importance of attributes, discovers the patterns of data, reduces all redundant objects and attributes, and seeks the minimum subset of attributes. Moreover, it is being used for the extraction of rules from databases. In this paper, we present a rough set approach to attribute reduction and generation of classification rules from a set of medical datasets. For this purpose, we first introduce a rough set reduction technique to find all reducts of the data that contain the minimal subset of attributes associated with a class label for classification. To evaluate the validity of the rules based on the approximation quality of the attributes, we introduce a statistical test to evaluate the significance of the rules. Experimental results from applying the rough set approach to the set of data samples are given and evaluated. In addition, the rough set classification accuracy is also compared to the well‐known ID3 classifier algorithm. The study showed that the theory of rough sets is a useful tool for inductive learning and a valuable aid for building expert systems.