Fa-Chao Li

A generalized fuzzy ID3 algorithm using generalized information entropy

A fuzzy decision tree is an important tool for knowledge acquisition in uncertain environments. Most of the existing fuzzy decision tree algorithms do not systematically consider the impact of the non-linear characteristics of the membership degree of fuzzy sets; they are therefore unable to integrate uncertainty processing preferences into the selection of extended attributes. This paper initially offers a generalized Hartley metric model and calculation method. We then introduce a fuzzy consciousness function and further provide generalized fuzzy partition entropy for the attribute-selecting heuristic of a fuzzy decision tree. We subsequently propose a generalized fuzzy partition entropy-based fuzzy ID3 algorithm (abbreviated as GFID3) that can support decision making and analyze the performance of the GFID3 through several case-based examples. The experimental results show that the GFID3 algorithm demonstrates better structural characteristics and operability in practical applications and has high computational precision. It ameliorates the deficiencies of existing fuzzy decision tree algorithms and can be used in fields such as complex systems optimization, data mining and intelligent systems.

Oxidation Desulfurization of Thiophene Using Phase Transfer Catalyst/H2O2 Systems

Abstract In our study, an effective phosphomolybdic acid/hexadecyltrimethyl-ammonium bromide catalyst for oxidative desulfurization of thiophene in a model compound was formed. The oxidation activities of thiophene for a series of heteropoly acids were estimated. The results show that the oxidation activity of thiophene increased with increasing oxidation time, oxidation temperature, and the volume of 30% H2 O2 oxidant. The optimal values are 150 min, 40°C, and 3 mL, and sulfur removal attained 96.3% when phosphotungstic acid/hexadecyltrimethylammonium bromide was used as a catalyst.

Feature selection with partition differentiation entropy for large-scale data sets

Feature selection, especially for large data sets, is a challenging problem in areas such as pattern recognition, machine learning and data mining. With the development of data collection and storage technologies, the data has become bigger than ever, thus making it difficult for learning from large data sets with traditional methods. In this paper, we introduce the partition differentiation entropy from the viewpoint of partition in rough sets to measure the significance and uncertainty of attributes, and present a feature selection method for large-scale data sets based on the information-theoretical measurement of attribute significance. Given a large-scale decision information system, the proposed method first divides it into small sub information systems according to the decision classes. Then by computing partition differentiation entropy in the sub-systems, the partition differentiation entropy of the attribute subset in the original decision information system is obtained. Accordingly, the important features are selected based on the value of partition differentiation entropy. The experimental results show that the idea of the proposed method is feasible and valid.

Optimization of Oxidative Desulfurization of Dibenzothiophene Using a Coordinated Ionic Liquid as Catalytic Solvent

Abstract Oxidative desulfurization (ODS) of dibenzothiophene (DBT) in n-octane with hydrogen peroxide/acetic acid using a quaternary ammonium coordinated ionic liquid (IL) (C4H9)4NBr · 2C6H11NO as catalytic solvent has been studied. The ODS mechanism by coordinated ionic liquid [(C4H9)4NBr · 2C6H11NO] was also carried out. The sulfur-containing compounds in model oil were extracted into ionic liquid phase and oxidized to their corresponding sulfones by H2O2. The effect factors for desulfurization of model oil were investigated in detail by means of monofactorial and orthogonal experiments (L16(4)4). The results showed that the desulfurization efficiency of model oil could reach 98.6% under the optimal conditions of oxidation time, oxidation temperature, molar ratio of H2O2/sulfur (O/S), and volume ratio of model oil to coordinated ionic liquid were 30 min, 50°C, 16, and 1, respectively. The influences to the desulfurization efficiency of DBT decreased in the following order: volume ratio of model oil to coordinated ionic liquid (C4H9)4NBr · 2C6H11NO (Vmodel oil/VIL) > molar ratio of O/S > oxidation temperature > oxidation time, according to extreme analysis of the orthogonal test. The coordinated ionic liquid (C4H9)4NBr · 2C6H11NO can be recycled 5 times without a significant decrease in desulfurization.

One-Step Oxidative Desulfurization of Dibenzothiophene Using Cyclohexanone Peroxide in N-Alkyl-imidazolium–Based Ionic Liquid Extraction Systems

Abstract One-step oxidative desulfurization of dibenzothiophene (DBT) using cyclohexanone peroxide (CYHPO) was performed in the presence of N-alkyl-imidazolium-based ionic liquids (ILs). CYHPO is an oil-soluble oxidant and ILs are employed as extractants. The effect of the ILs, the molar ratio of CYHPO/S (O/S), volume ratio (VIL/Vmodel oil), reaction time (T), and reaction temperature (t) were investigated in detail. The results showed that the desulfurization ability of the ILs followed the order [OMim]BF4 > [HMim]BF4 > [BMim]BF4, reversing the length of the alkyl group to the imidazolium ring. When IL [OMim]BF4 was used, O/S was 2 and VIL/Vmodel oil was 1:1, and 93.5% of DBT in the model oil was removed at 40°C for 30 min. The desulfurization rate of gasoline was 70.8% under optimal conditions. IL ([OMim]BF4) could be recycled for five times without a significant decrease in activity.

A density clustering based niching genetic algorithm for multimodal optimization

A new density clustering based niching method for genetic algorithm is proposed in this paper, which is able to identify and track global and local optima for a multimodal function. To prevent the loss of diversity the global selection pressure within a single population is replaced by local selection of a multipopulation strategy. The subpopulations representing species specialized on niches are dynamically identified using density based clustering algorithm on a primordial population. Moreover, a new method is designed for automatically calculating clustering threshold. Finally, the presented algorithm is applied to the optimizations of typical multimodal functions compared with SH and DC algorithms, and the results reveal its efficiency and effectiveness.

A QUANTITY PROPERTY-BASED FUZZY NUMBER RANKING METHOD FOR DECISION MAKING WITH UNCERTAINTY

One of the key issues for support fuzzy decision-making is fuzzy number ranking. The existing ranking methods either do not provide a total ordering or cannot be effectively applied to decision-making processes. In this paper, we first give five basic principles that interval number ranking must satisfy, and construct a quantitative ranking model of interval numbers based on the synthesis effects of each index. We then propose a new constructions method of synthesis effect function systematically. Third, we also develop a new fuzzy numbers ranking model based on numerical characteristics, combining with the interval representation theorem of fuzzy numbers, and analyze the performance and characteristics of this ranking method by a case-based example. The results indicate that this proposed ranking method has good operability and interpretability, which can integrate the decision consciousness into decision process effectively and serve as a guideline for constructing different fuzzy decision methods.

Parameter Optimization for SVM using Sequential Number Theoretic for Optimization

In this paper, we propose a support vector machine (SVM) meta-parameter optimization method which uses sequential number theoretic optimization (SNTO) and gradient information for better optimization performance. SNTO is a new global optimization approach whose foundation is numeric and statistic theory. This method has less computation time than genetic algorithm (GA) based and grid search based methods and better performance on finding global optimal value than gradient based methods. Simulations demonstrate that it is robust and works effectively and efficiently on a variety of problems

Oxidative Desulfurization of Model Gasoline Over Modified Titanium Silicalite

The oxidative desulfurization of model gasoline consisting of thiophene dissolved in n-octane was investigated with a series of modified titanium silicalite (TS) catalysts in presence of hydrogen peroxide and formic acid systems, and the reaction mechanism of the oxidative desulfurization of thiophene was preliminarily researched. The results showed that the copper modified TS was an active catalyst for thiophene oxidation while the other metal modified TSs were less active catalysts. When Cu-TS at a Cu/Si molar ratio of 0.015 was used as a catalyst for oxidation of model gasoline, the conversion of thiophene was 94.1% at 120 min. The conversion of thiophene was easily enhanced by increasing reaction time or reaction temperature, and reduced with addition of xylene and cyclohexene.

The Photooxidative Desulfurization of Thiophene with Tetrabutylammonium Bromide as a Phase Transfer Catalyst

Abstract Photochemical oxidative desulfurization of thiophene with tetrabutylammonium bromide (TBAB) as phase transfer catalyst was studied. The effects of the TBAB addition and pH on the desulfurization yield of thiophene were investigated. The cycle model of desulfurization of thiophene with TBAB was proposed. The results show that the desulfurization yield of thiophene in n-octane is 80.6% for a 2-hr photoirradiation under the conditions of air flow at 150 mL/min, V (n-octane):V (water) = 1:1, pH = 12, and 0.1 g of TBAB as catalyst. The photooxidation kinetics of thiophene is first-order with rate constant of 0.5702 hr−1 and half-life of 1.22 hr.