The Experts below are selected from a list of 91140 Experts worldwide ranked by ideXlab platform

Alex A. Freitas - One of the best experts on this subject based on the ideXlab platform.

  • a hybrid decision tree Genetic Algorithm Method for data mining
    Information Sciences, 2004
    Co-Authors: Deborah R. Carvalho, Alex A. Freitas
    Abstract:

    This paper addresses the well-known classification task of data mining, where the objective is to predict the class which an example belongs to. Discovered knowledge is expressed in the form of high-level, easy-to-interpret classification rules. In order to discover classification rules, we propose a hybrid decision tree/Genetic Algorithm Method. The central idea of this hybrid Method involves the concept of small disjuncts in data mining, as follows. In essence, a set of classification rules can be regarded as a logical disjunction of rules. so that each rule can be regarded as a disjunct. A small disjunct is a rule covering a small number of examples. Due to their nature, small disjuncts are error prone. However, although each small disjunct covers just a few examples, the set of all small disjuncts can cover a large number of examples, so that it is important to develop new approaches to cope with the problem of small disjuncts. In our hybrid approach, we have developed two Genetic Algorithms (GA) specifically designed for discovering rules covering examples belonging to small disjuncts, whereas a conventional decision tree Algorithm is used to produce rules covering examples belonging to large disjuncts. We present results evaluating the performance of the hybrid Method in 22 real-world data sets.

  • a hybrid decision tree Genetic Algorithm for coping with the problem of small disjuncts in data mining
    Genetic and Evolutionary Computation Conference, 2000
    Co-Authors: Deborah R. Carvalho, Alex A. Freitas
    Abstract:

    The problem of small disjuncts is a serious challenge for data mining Algorithms. In essence, small disjuncts are rules covering a small number of examples. Due to their nature, small disjuncts tend to be error prone and contribute to a decrease in predictive accuracy. This paper proposes a hybrid decision tree/Genetic Algorithm Method to cope with the problem of small disjuncts. The basic idea is that examples belonging to large disjuncts are classified by rules produced by a decision-tree Algorithm, while examples belonging to small disjuncts (whose classification is considerably more difficult) are classified by rules produced by a Genetic Algorithm specifically designed for this task.

Deborah R. Carvalho - One of the best experts on this subject based on the ideXlab platform.

  • a hybrid decision tree Genetic Algorithm Method for data mining
    Information Sciences, 2004
    Co-Authors: Deborah R. Carvalho, Alex A. Freitas
    Abstract:

    This paper addresses the well-known classification task of data mining, where the objective is to predict the class which an example belongs to. Discovered knowledge is expressed in the form of high-level, easy-to-interpret classification rules. In order to discover classification rules, we propose a hybrid decision tree/Genetic Algorithm Method. The central idea of this hybrid Method involves the concept of small disjuncts in data mining, as follows. In essence, a set of classification rules can be regarded as a logical disjunction of rules. so that each rule can be regarded as a disjunct. A small disjunct is a rule covering a small number of examples. Due to their nature, small disjuncts are error prone. However, although each small disjunct covers just a few examples, the set of all small disjuncts can cover a large number of examples, so that it is important to develop new approaches to cope with the problem of small disjuncts. In our hybrid approach, we have developed two Genetic Algorithms (GA) specifically designed for discovering rules covering examples belonging to small disjuncts, whereas a conventional decision tree Algorithm is used to produce rules covering examples belonging to large disjuncts. We present results evaluating the performance of the hybrid Method in 22 real-world data sets.

  • a hybrid decision tree Genetic Algorithm for coping with the problem of small disjuncts in data mining
    Genetic and Evolutionary Computation Conference, 2000
    Co-Authors: Deborah R. Carvalho, Alex A. Freitas
    Abstract:

    The problem of small disjuncts is a serious challenge for data mining Algorithms. In essence, small disjuncts are rules covering a small number of examples. Due to their nature, small disjuncts tend to be error prone and contribute to a decrease in predictive accuracy. This paper proposes a hybrid decision tree/Genetic Algorithm Method to cope with the problem of small disjuncts. The basic idea is that examples belonging to large disjuncts are classified by rules produced by a decision-tree Algorithm, while examples belonging to small disjuncts (whose classification is considerably more difficult) are classified by rules produced by a Genetic Algorithm specifically designed for this task.

Wei Liu - One of the best experts on this subject based on the ideXlab platform.

  • a hybrid system using direct contact membrane distillation for water production to harvest waste heat from the proton exchange membrane fuel cell
    Energy, 2018
    Co-Authors: Xiaotia Lai, Rui Long, Zhichu Liu, Wei Liu
    Abstract:

    Abstract In this paper, a hybrid system consisting of PEMFC (proton exchange membrane fuel cell) and DCMD (direct contact membrane distillation) was proposed to recover the waste heat from PEMFC for brine water desalination. Parameters determining the performance of this hybrid system were systematically investigated. Results indicate that there exist optimal PEMFC current density and DCMD fresh water inlet mass flow rate, respectively, leading to the maximum energy gain from the fuel chemical energy. In order to analyze the optimal performance of the proposed hybrid system, with the maximum energy gain as the objective function, Genetic Algorithm Method was employed to obtain the optimal PEMFC current density and DCMD fresh solution inlet mass flow rate, thereby, the performance specifications of the hybrid system under different operating temperatures of the PEMFC subsystem. Compared with the single PEMFC system, as operating temperature varies from 328.15 K to 348.15 K, the energy utilization degree can be increased by 201%–266%.

  • performance analysis of a dual loop thermally regenerative electrochemical cycle for waste heat recovery
    Energy, 2016
    Co-Authors: Rui Long, Zhichun Liu, Wei Liu
    Abstract:

    Abstract A DLTREC (dual loop thermally regenerative electrochemical cycle) system consisting of two hot electrochemical cells and a cold one is proposed for harvesting waste heat in a more efficient manner. With the maximum power output as the objective function, an optimal analysis of the DLTREC system based on a GA (Genetic Algorithm) Method was conducted for different inlet temperatures of the heat source. For comparison, an optimization analysis of conventional TREC (thermally regenerative electrochemical cycle) systems was also conducted under equivalent criterion. The maximum output, the corresponding electrical and exergy efficiencies, and exergy destruction of the two energy harvesting systems were analyzed and compared. Results revealed that the DLTREC system can increase the power output and decrease the irreversibility. For the prescribed heat source inlet temperature of 393.15 K, the maximum power output of the DLTREC system was 50.11% larger than that of the conventional TREC system and the electrical efficiency was improved by 13.31%. The exergy efficiency of the DLTREC system was 19.41% larger than that of a conventional TREC system.

  • a hybrid system using a regenerative electrochemical cycle to harvest waste heat from the proton exchange membrane fuel cell
    Energy, 2015
    Co-Authors: Rui Long, Zhichun Liu, Wei Liu
    Abstract:

    Abstract A new hybrid system consisting of a PEMFC (proton exchange membrane fuel cell) subsystem and a TREC (thermally regenerative electrochemical cycle) subsystem is proposed to convert the waste heat produced by the PEMFC system into electricity. The performance of the hybrid system and its corresponding subsystems is analyzed. Results reveal that there exists optimal current densities of the PEMFC and TREC systems leading to the maximum power output of the hybrid system. With the maximum power output as the objective function, an optimization of the hybrid system based on Genetic Algorithm Method is conducted under different operating temperatures of the PEMFC subsystem. The power output of the hybrid system is 6.85%–20.59% larger than that of the PEMFC subsystem. And the total electrical efficiency is improved by 2.74%–8.27%. The corresponding electrical efficiency of the TREC is 4.56%–13.81%. The hybrid system proposed in this paper could contribute to utilizing the fuel energy more efficiently and sufficiently.

Ceyhun Yilmaz - One of the best experts on this subject based on the ideXlab platform.

  • a case study exergoeconomic analysis and Genetic Algorithm optimization of performance of a hydrogen liquefaction cycle assisted by geothermal absorption precooling cycle
    Renewable Energy, 2018
    Co-Authors: Ceyhun Yilmaz
    Abstract:

    Abstract The present paper deals with the hydrogen liquefaction system with absorption precooling cycle assisted by geothermal energy is modeled and analyzed as an exergoeconomic. Uses part of the geothermal water heat for absorption refrigeration to precool the hydrogen gas and part of the geothermal water heat to produce work with a binary geothermal cycle and use it in a liquefaction cycle. Exergoeconomic optimization procedure is applied using Genetic Algorithm Method to the integrated system. The objective is to minimize the unit cost of hydrogen liquefaction of the composed system. Based on optimization calculations, hydrogen gas can be cooled down to −30 °C in the precooling cycle. The actual work consumption in the hydrogen liquefaction is calculated to be 10.06 kWh/kg LH2. The unit exergetic liquefaction cost of hydrogen is calculated to be 1.114 $/kg LH2 or 9.27 $/GJ, respectively in the optimum case.

  • performance analysis and optimization of a hydrogen liquefaction system assisted by geothermal absorption precooling refrigeration cycle
    International Journal of Hydrogen Energy, 2018
    Co-Authors: Ceyhun Yilmaz, Önder Kaşka
    Abstract:

    Abstract The present paper deals with the hydrogen liquefaction with absorption precooling cycle assisted by geothermal water is modeled and analyzed. Uses geothermal heat in an absorption refrigeration process to precool the hydrogen gas is liquefied in a liquefaction cycle. High-temperature geothermal water using the absorption refrigeration cycle is used to decrease electricity work consumption in the gas liquefaction cycle. The thermoeconomic optimization procedure is applied using the Genetic Algorithm Method to the hydrogen liquefaction system. The objective is to minimize the unit cost of hydrogen liquefaction of the composed system. Based on optimization calculations, hydrogen gas can be cooled down to −30 °C in the precooling cycle. This allows the exergetic cost of hydrogen gas to be reduced to be 20.16 $/GJ (2.42 $/kg LH2). The optimized exergetic cost of liquefied hydrogen is 4.905 $/GJ (1.349 $/kg LH2), respectively.

Majid Amidpour - One of the best experts on this subject based on the ideXlab platform.

  • configurations and pressure levels optimization of heat recovery steam generator using the Genetic Algorithm Method based on the constructal design
    Applied Thermal Engineering, 2017
    Co-Authors: Morteza Mehrgoo, Majid Amidpour
    Abstract:

    Abstract In last two decades, there was a great deal of attention on the optimum design and performance improvement of the heat recovery steam generator (HRSG) units. In the present work, considering different objective functions and utilizing the constructal design Method, three configurations of HRSG are compared. The design Method is based on the constructal theory and optimization technique is carried out by varying the geometric design parameters and steam pressure levels for different values of the exhaust gas temperatures. Optimum conditions of HRSG are obtained with the help of the Genetic Algorithm under the fixed total volume constraint. For each configuration of HRSG, optimal distribution of the heat surfaces (sizes) subject to the total volume constraint are derived such that the objective function is optimum. It is shown that how the geometric and thermodynamic design variables of HRSG can be achieved, simultaneously. Features that resulted from the constructal design are the number of tubes, configurations and aspect ratios for the main sections, the tube diameters and rate of the steam production at each pressure level. The results revealed that variations in different objective functions are strongly affected by the hot gas inlet temperature. In addition, the use of several pressure levels in HRSGs causes a considerable increase in the power production, declines irreversibility in HRSGs and allows producing higher steam flow rate for all values of the inlet gas temperature. The constructal principle invoked in this paper represents that geometrical form of systems can be deduced from a single principle.

  • derivation of optimal geometry of a multi effect humidification dehumidification desalination unit a constructal design
    Desalination, 2011
    Co-Authors: Morteza Mehrgoo, Majid Amidpour
    Abstract:

    Abstract This paper introduces a model and a structured procedure to optimize the shape and structure (relative sizes, aspect ratios) of a multi-effect humidification–dehumidification (MEH) desalination unit. The constructal approach is used for this investigation. Considering maximum production rate as the objective function, optimum design parameters of the MEH unit are derived by using the Genetic Algorithm Method under the fixed total volume condition. The available volume is optimally distributed through the system so that the production rate is maximized. The results showed that the inlet cold and hot water temperatures and the column heights play important roles in the constructal design of a MEH unit, especially as the total volume increases. Moreover, the tube diameters and the number of condenser tubes should be suitably selected based on the values of the condenser, the humidifier inlet water temperatures and the column heights. The constructal principle invoked in this paper represents that geometrical form of systems can be deduced from a single principle and provides designers with tools for their conceptual design.