Efficient Numerical Optimization Algorithm Based on New Real-Coded Genetic Algorithm, AREX + JGG, and Application to the Inverse Problem in Systems Biology

In Systems Biology, system identification, which infers regulatory network in genetic system and metabolic pathways using experimentally observed time-course data, is one of the hottest issues. The efficient numerical optimization algorithm to estimate more than 100 real-coded parameters should be developed for this purpose. New real-coded genetic algorithm (RCGA), the combination of AREX (adaptive real-coded ensemble crossover) with JGG (just generation gap), have applied to the inference of genetic interactions involving more than 100 parameters related to the interactions with using experimentally observed time-course data. Compared with conventional RCGA, the combination of UNDX (unimodal normal distribution crossover) with MGG (minimal generation gap), new algorithm has shown the superiority with improving early convergence in the first stage of search and suppressing evolutionary stagnation in the last stage of search.

Adaptive Real-Coded Genetic Algorithm for Identifying Motor Systems

In this paper, the main objective is to identify the parameters of motors, which includes a brushless direct current (BLDC) motor and an induction motor. The motor systems are dynamically formulated by the mechanical and electrical equations. The real-coded genetic algorithm (RGA) is adopted to identify all parameters of motors, and the standard genetic algorithm (SRGA) and various adaptive genetic algorithm (ARGAs) are compared in the rotational angular speeds and fitness values, which are the inverse of square differences of angular speeds. From numerical simulations and experimental results, it is found that the SRGA and ARGA are feasible, the ARGA can effectively solve the problems with slow convergent speed and premature phenomenon, and is more accurate in identifying system’s parameters than the SRGA. From the comparisons of the ARGAs in identifying parameters of motors, the best ARGA method is obtained and could be applied to any other mechatronic systems.

Supervised Fuzzy Mixture of Local Feature Models

This paper addresses an important issue in model combination, that is, model locality. Since usually a global linear model is unable to reflect nonlinearity and to characterize local features, especially in a complex sys-tem, we propose a mixture of local feature models to overcome these weaknesses. The basic idea is to split the entire input space into operating domains, and a recently developed feature-based model combination method is applied to build local models for each region. To realize this idea, three steps are required, which include clustering, local modeling and model combination, governed by a single objective function. An adaptive fuzzy parametric clustering algorithm is proposed to divide the whole input space into operating regimes, local feature models are created in each individual region by applying a recently developed fea-ture-based model combination method, and finally they are combined into a single mixture model. Corre-spondingly, a three-stage procedure is designed to optimize the complete objective function, which is actu-ally a hybrid Genetic Algorithm (GA). Our simulation results show that the adaptive fuzzy mixture of local feature models turns out to be superior to global models.

Recent Advances in Global Optimization for Combinatorial Discrete Problems

The optimization of discrete problems is largely encountered in engineering and information domains. Solving these problems with continuous-variables approach then convert the continuous variables to discrete ones does not guarantee the optimal global solution. Evolutionary Algorithms (EAs) have been applied successfully in combinatorial discrete optimization. Here, the mathematical basics of real-coding Genetic Algorithm are presented in addition to three other Evolutionary Algorithms: Particle Swarm Optimization (PSO), Ant Colony Algorithms (ACOA) and Harmony Search (HS). The EAs are presented in as unifying notations as possible in order to facilitate understanding and comparison. Our combinatorial discrete problem example is the famous benchmark case of New-York Water Supply System WSS network. The mathematical construction in addition to the obtained results of Real-coding GA applied to this case study (authors), are compared with those of the three other algorithms available in literature. The real representation of GA, with its two operators: mutation and crossover, functions significantly faster than binary and other coding and illustrates its potential as a substitute to the traditional optimization methods for water systems design and planning. The real (actual) representation is very effective and provides two near-optimal feasible solutions to the New York tunnels problem. We found that the four EAs are capable to afford hydraulically-feasible solutions with reasonable cost but our real-coding GA takes more evaluations to reach the optimal or near-optimal solutions compared to other EAs namely the HS. HS approach discovers efficiently the research space because of the random generation of solutions in every iteration, and the ability of choosing neighbor values of solution elements “changing the diameter of the pipe to the next greater or smaller commercial diameter” beside keeping good current solutions. Our proposed promising point to improve the performance of GA is by introducing completely new individuals in every generation in GA using a new “immigration” operator beside “mutation” and “crossover”.

REAL CODED GENETIC ALGORITHM FOR STOCHASTIC HYDROTHERMAL GENERATION SCHEDULING

The intent of this paper is to schedule short-term hydrothermal system probabilistically considering stochastic operating cost curves for thermal power generation units and uncertainties in load demand and reservoir water inflows. Therefore, the stochastic multi-objective hydrothermal generation scheduling problem is formulated with explicit recognition of uncertainties in the system production cost coefficients and system load, which are treated as random variable. Fuzzy methodology has been exploited for solving a decision making problem involving multiplicity of objectives and selection criterion for best compromised solution. A real-coded genetic algorithm with arithmetic-average-bound-blend crossover and wavelet mutation operator is applied to solve short-term variable-head hydrothermal scheduling problem. Initial feasible solution has been obtained by implementing the random heuristic search. The search is performed within the operating generation limits. Equality constraints that satisfy the demand during each time interval are considered by introducing a slack thermal generating unit for each time interval. Whereas the equality constraint which satisfies the consumption of available water to its full extent for the whole scheduling period is considered by introducing slack hydro generating unit for a particular time interval. Operating limit violation by slack hydro and slack thermal generating unit is taken care using exterior penalty method. The effectiveness of the proposed method is demonstrated on two sample systems.

A New Method of Portfolio Optimization Under Cumulative Prospect Theory

In this paper, the portfolio selection problem under Cumulative Prospect Theory （CPT） is investigated and a model of portfolio optimization is presented. This model is solved by coupling scenario generation techniques with a genetic algorithm. Moreover, an Adaptive Real-Coded Genetic Algorithm （ARCGA） is developed to find the optimal solution for the proposed model. Computational results show that the proposed method solves the portfolio selection model and that ARCGA is an effective and stable algorithm. We compare the portfolio choices of CPT investors based on various bootstrap techniques for scenario generation and empirically examine the effect of reference points on investment behavior.