Research and Implement on Genetic Algorithm and Ant Colony Algorithm in Chinese Question Answering System

Robot coalition problem is a complicated combinatorial optimization problem. In this paper, a novel quantum ant colony algorithm for the problem is proposed, where the thought of quantum evolution algorithm is combined with ant colony algorithm. In this algorithm, the pheromone is encoded by quantum bits and a new pheromone representation is designed. To avoid the algorithm falling into local optimum, the strategy of quantum crossover is designed to improve the information structure of population. Simulation results show that the algorithm is more effective than quantum genetic algorithm and basic ant colony algorithm.

Precocity, stagnation and phenomenon of long time convergence often emerge from classical genetic algorithm or ant colony algorithm. At the same time, they have different features of convergence in each algorithm. So, a coevolutionary model is presented based on genetic algorithm and ant colony algorithm, which runs one of the above two algorithm and exchanges another by estimating the state of their running. In order to search optimal result of problem, genetic algorithm and ant colony algorithm can run conjunctly in the model. Through the experimentation on symmetric and asymmetric TSP, the outcome shows that compared with other algorithm, the algorithm of the model takes a great improvement in the convergent speed, result optimization and also the avoidance of the precocity and stagnation.

In order to solve the optimization of new energy bus line network, a new energy bus line network based on ant colony algorithm and low-carbon concept is proposed. Firstly, the model of public transport network is established combined with OD matrix, and the improved ant colony algorithm is used to iteratively optimize the initial suboptimal route set, optimize the objective function, and finally obtain the optimal public transport route set. Secondly, the improved ant colony algorithm based on simulated annealing solves the design of public transport network, and the optimization scheme greatly reduces the number of passenger transfers and the total travel time of passengers. Finally, simulated annealing algorithm, basic ant colony algorithm, and simulated annealing improved ant colony algorithm are used to optimize the objective function. It is proved that the improved ant colony algorithm of simulated annealing can find the optimal solution of the three algorithms when solving the problem of public transport network design, which is better than the solution of basic ant colony and simulated annealing algorithm. The solution efficiency is 10.6 times that of simulated annealing algorithm and 3.5 times that of basic ant colony algorithm.

Under the premise of using Ford algorithm to obtain the shortest path in the link map, in this paper the path adjustment algorithm which is the combination of the genetic algorithm and ant colony algorithm is introduced. And the path adjustment algorithm is used to adjust and optimize the current shortest path. The definition of the genetic algorithm control function was to control the appropriate combination opportunity of the two algorithms. Taking advantage of genetic algorithm to produce the original results, they were transformed into the initial pheromones value needed by ant colony algorithm, then ant colony algorithm to get the best results. Through numerical simulation analysis, it is further description that the path adjustment algorithm's effectiveness and necessity.

Airport information weak current system is the core of airport terminal, which is responsible for information interaction, power resource and energy consumption management among subsystems of airport terminal. Meanwhile, it is also responsible for main business dispatch management of entire airport terminal. Therefore, starting with basic ant colony algorithm and considering respective advantages of genetic and ant colony algorithms, optimization cycle of the two algorithms is introduced multiple times in this paper. Moreover, after each loop iteration of ant colony algorithm, optimal solution generated by ant colony algorithm will be added to genetic algorithm so that iterative speed of genetic algorithm can be accelerated. Meanwhile, solution calculated by genetic algorithm will be set to better path to update pheromone allocation in ant colony algorithm and achieve parameter adjustment. Experimental test proves that geneticant colony hybrid algorithm proposed in this paper has good convergence and solution efficiency, which can find the shortest path with suitable conditions in complex road networks.

The partner selection in virtual enterprises organization is one of the key issues corporate enterprises experience nowadays. Based on the model of Ant Colony Optimization Algorithm (ACA) in virtual enterprise partner selection, in this paper, we fuse the genetic algorithm into ACA, called fusion algorithm, in order to improve the effect of the partner selection. The fusion algorithm has two steps: 1) it uses the GA to optimize the model of partner selection and takes advantages of rapid convergence of GA in initial search periods. 2) When GA search speed has become slow, the ACA takes over the search process, in which it uses the candidates produced by the GA as the seeds of pheromone used by ACA. By experimental comparison with GA optimization and ACA optimization, it shows that the fusion algorithm has performed better than the GA and ACA optimization, respectively, in both speed and accuracy under our selected numerical case. The fusion algorithm presented in this study may be applicable to similar business problems.

In view of the disadvantages of the basic ant colony algorithm in solving non-deterministic polynomial problems, such as slow convergence rate and local optimal solution. In this paper, the updating rules of pheromone and the updating strategy of target city in ant colony algorithm are improved, and an improved ant colony algorithm (IACA) is proposed. In addition, it is applied to the shortest traversal path search of travel salesman problem. Taking 33 provincial capitals and berlin52 problems as test objects, this paper compares the search efficiency of the proposed algorithm with that of the basic ant colony algorithm. It can be seen from the simulation results that IACA has a faster convergence rate than the basic ant colony algorithm. IACA is obviously superior to the basic ant colony algorithm in terms of convergence and the quality of the optimal solution. It provides a new choice for solving similar optimization problems.

Improved random selection strategy, self-adaptive crossover and mutation operators, population co-evolution algorithm are adopted in this paper to set up a new genetic algorithm(GA), guaranteeing the universality of population, the thoroughness of solution and the execution efficiency of algorithm in solving multi-process, process crossover, work-piece flow and other condition based scheduling problem of flexible manufacturing system(FMS). The problem of GA in solving FMS scheduling is summarized in this paper, reasons and countermeasures for GA's pre-maturing are studied, longitudinal and transverse comprehensive state-based correlative self-adaptive crossover and mutation operators are raised according to the analysis on GA to avoid local optimization and pre-maturity, the co-evolutionary GA is designed to solve the scheduling model for FMS, and the algorithm is validated for the scheduling of box-type parts for precise machine tools.

Ant colony optimization (ACO) algorithm is a metaheuristic inspired by the behavior of real ants in their search for the shortest path to food sources. The ACO algorithm takes on these characteristics of robust, positive feedback distributed computing, easy fusing with other algorithms. But the basic ACO algorithm has some deficiencies of premature and stagnation phenomenon in the evolution process, and is easily trapped into local optimal solution. And it is difficult to explore other solutions in the neighbor space. So a improved ACO(DPSEMACO) algorithm based on dual population strategy, bi-directional dynamic adjust evaporation factor strategy of the pheromone and parallel strategy is proposed to solve the traveling salesman problem(TSP). In the DPSEMACO algorithm, the ants are divided into the two subpopulations by borrowing the mutual cooperation mechanism of biological community, which evolve separately and exchange information timely. The bi-directional dynamic adjusting evaporation factor strategy of the pheromone is used to change the corresponding path pheromone of different subpopulations in order to avoid to trap into a local optimum. The parallel strategy can avoid falling into a local optimum. And the DPSEMACO algorithm can expand the search space and improve the overall searching performance by repeated changing the pheromone of the each subpopulation and adaptive adjusting evaporation factor. Finally, in order to prove the optimization performance of the proposed DPSEMACO algorithm, some classic TSP instances are selected from the TSPLIB in this paper. And some existing methods are selected to compare the optimization performance with the proposed DPSEMACO algorithm. The experimental results demonstrate that the proposed DPSEMACO algorithm is feasible and effective in solving TSP, and takes on a good global searching ability and high convergence speed.

The main core of software engineering key technologies is the development of software services, ensuring the scientificity, security, and stability of the application software engineering system. At present, China’s economic development urgently needs the support of software engineering technology. Based on the T-ACO algorithm, the scientificity of software engineering and the accuracy of data have been significantly improved compared with traditional software engineering technology. It plays an important role in promoting the follow-up software engineering technology. In order to effectively analyze the key technology of engineering software, an improved ant colony algorithm based on T distribution is proposed in this paper. Because the basic ant colony algorithm is easy to fall into the local optimum and the optimization accuracy is low, in the optimization process, at the beginning of the pheromone update, the introduction of the T distribution is helpful for the basic ant colony algorithm to make up for its shortcomings. Adding pheromone variables to the basic ant colony algorithm improves the diversity of the ant colony, thereby eliminating the limitations of local optimal solutions. At the same time, the T-ACO algorithm also improves the search accuracy and convergence speed of automatic data generation in software engineering. In this paper, the performance of the T-ACO algorithm is simulated by experiments. Experimental analysis shows that when the population size is small, the T-ACO algorithm may sometimes not converge to the optimal solution, but when the population size is large (≥50), the T-ACO algorithm may converge to the optimal solution. It can realize the coverage of the total path by the output test case set. While the other two algorithms can achieve full path coverage, they are not stable, resulting in an average coverage between 90% and 100%. The T-ACO algorithm not only has good accuracy in creating test case sets, but also has good algorithm performance, and it is suitable as a multipath test case creation algorithm.

Interconnect test technology has become a bottleneck in the application of MCM. In this paper, a new multichip module (MCM) interconnect test generation approach based on ant colony algorithm (ACA) with crossover and mutation operator is presented. By combing the characteristics of MCM interconnect test, the pheromone updating rule and state transition rule of ant colony algorithm is designed. Using crossover and mutation operator, this approach overcomes ordinary ant colony algorithm's defects of slow convergence speed, easy to get stagnate, and low ability of full search. The international standard MCM benchmark circuit provided by the MCNC group was used to verify the approach. The results of simulation experiments, which compare to the results of standard ant colony algorithm, genetic algorithm (GA) and other deterministic interconnecting test generation algorithms, show that the proposed approach can achieve higher fault coverage and more compact test sets

In the field of health care, the Wireless Body Area Networks(WBANs), through placed miniaturization, low power consumption of sensor nodes in patient's body or on the surface to measure a variety of physiological parameters, to monitor or diagnose the health of human body. However, in this process, WBANs nodes usually use batteries, especially for implantable flexible node it is difficult to accomplish the replacement of batteries, the energy that the node can carry is very limited, so the efficient use of energy is the most important problem to consider when designing WBANs routing algorithm. By considering the factors such as residual energy of node, the importance level of node, path cost and path energy difference ratio, this paper gives the definition of Optimal Path of Energy Consumption(OPEC) in WBANs, and The Optimal Energy Consumption Artificial Bee Colony(ABC) Based WBANs(OEABC) is designed. The performance simulation is carried out to verify the effectiveness of the OEABC, compared with Genetic Algorithm and Ant Colony Algorithm, it shows that t the OEABC has a fast convergence rate.

The traveling salesman problem (TSP) is an NP-hard problem. Thus far, a large number of researchers have proposed different ant colony optimization (ACO) algorithms to solve the TSP. These algorithms inevitably encounter problems such as long convergence time and the tendency to easily fall into local optima. On the basis of the ACO algorithm, this study proposes a dynamic adaptive ACO algorithm (DAACO). DAACO realizes the diversity of initialization of the ACO algorithm by dynamically determining the number of ants to be prevented from falling into local optimization. DAACO also adopts a hybrid local selection strategy to increase the quality of ant optimization and reduce the optimization time. Among the 20 instances of the TSPLIB dataset, the DAACO algorithm obtains 19 optimal values, and the solutions of 10 instances are better than those of other algorithms. The experimental results on the TSPLIB dataset show that the DAACO algorithm has obvious advantages in terms of convergence time, solution quality, and average value relative to existing state-of-the-art ACO algorithms.

Mobile robots are widely used in daily life, and ant colony algorithm is often adopted for its path planning. However, the classic ant colony algorithm has poor search ability and search speed due to the monotony of individuals within the population. In order to solve the problems of local optimal solution, slow convergence speed and low search efficiency of classic ant colony algorithm, a genetic-ant colony algorithm is proposed in this paper. The algorithm parameters are optimized by simulation experiment to determine the best parameter combination. The method is to give a certain range of random pheromone values to the primary ant individuals to enrich the population diversity. In each cycle, m ants are sent for foraging. After each foraging cycle, aiming at the growth of individual pheromone value, the fitness function of genetic algorithm is established to evaluate individual fitness value, and the parental individuals carry out genetic operations such as selection, crossover and variation to produce offspring individuals with the same number and higher pheromone level, the offspring individuals carry out the next cycle of foraging and keep cycling. The population diversity is maintained at a high level, while the increase in the level of individual pheromone speeds up the convergence and operation of the algorithm. The simulation results show that the running time of the improved algorithm is significantly shorter than that of the traditional ant colony algorithm in the 40 * 40 grid map, and the running time of the algorithm is reduced by 21.34%; in the complex grid environment, the frequency of obtaining the optimal path of the algorithm is significantly higher than that of ordinary ant colonies, and the frequency is increased; and the number of iterations when the optimal path is reached for the first time is significantly reduced,–which has verified the effectiveness, stability and superiority of genetic-ant colony algorithm.

Recently, medicine and health have been more and more concerned with people. This paper focuses on building a Chinese medical question answering system based on a knowledge graph. Firstly, a medical knowledge graph is built by structured data and is stored in the Neo4j, which contains 36825 entities, 210018 relationships, and collects 14366 kinds of diseases. When getting a question input, overlap-degree, edit-distance, cosine-similarity, are combined to match the target disease, with up to 75.49% accuracy. Tf-corpus algorithm is designed to extract features of the question, and the Naive Bayes Classifier is used to judge intention, with up to 76.84% accuracy. The answer can be found by disease and intention, and the Q & A task has been completed.