Solution Search Method Research Articles

Development of a solution search method using artificial intelligence

The object of the study is decision support systems. The problem of increasing decision-making efficiency in conditions of uncertainty and a set of different parameters was solved using a bio-inspired algorithm. The subject of the study is the decision-making process in management problems using the heron flock algorithm, the improved genetic algorithm and evolving artificial neural networks. A solution search method using the improved heron flock algorithm is proposed. The study is based on the heron flock algorithm to find a solution regarding the object state. Evolving artificial neural networks are used to train the heron flock algorithm, and an advanced genetic algorithm is used to select the best individuals of the heron flock. The method has the following sequence of actions: – input of initial data; – setting agents on the search plane; – numbering heron agents in the flock; – setting the initial velocity of heron agents; – waiting strategy for heron agents; – aggressive strategy; – checking the discriminatory condition; – selection of the best individuals from the heron flock; – ranking and sorting the obtained solutions; – training heron knowledge bases; – determining the amount of necessary computing resources of the intelligent decision support system. The originality of the proposed method consists in setting heron agents taking into account the uncertainty of the initial data, the noise degree of data about the analysis object state. The method makes it possible to reduce the time for decision-making at the level of 22–26 % due to the use of additional improved procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes in the interest of solving national security problems

Development of a solution search method using a combined bio-inspired algorithm

The object of the study is decision support systems. The subject of the study is the decision-making process in management problems using a combined bio-inspired algorithm, consisting of: – the improved wolf optimization algorithm and the improved sparrow search algorithm – for solving optimization problems regarding the object state; – an advanced genetic algorithm – for selecting the best agents in flocks; – an advanced training method – for deep training of agents to improve the optimization characteristics of agents. A solution search method using an improved bio-inspired algorithm is proposed. The method has the following sequence of actions: – input of initial data; – initialization of the search for a flock of sparrows and its parameters; – ranking and selection of sparrow agents using an advanced genetic algorithm; – updating the sparrow location for the discoverer; – checking the conditions for updating the position of sparrows; – initialization of additional search parameters; − running the gray wolf optimization algorithm; – training agents’ knowledge bases; – determining the amount of necessary computing resources of the intelligent decision support system. The originality of the proposed method lies in the combined use of bio-inspired algorithms, setting agents taking into account the uncertainty of the initial data, advanced global and local search procedures. The method makes it possible to increase the efficiency of data processing at the level of 19 % using additional improved procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes in the interest of solving national security problems

Development of a solution search method using the improved emperor penguin algorithm

The objects of the study are decision support systems. The subject of the study is the decision-making process in management problems using the Emperor Penguin Algorithm (EPA), an advanced genetic algorithm and evolving artificial neural networks. A solution search method using the improved EPA is proposed. The study is based on the EPA algorithm for finding a solution regarding the object state. Evolving artificial neural networks are used to train EPA, and an advanced genetic algorithm is used to select the best EPA. The method has the following sequence of actions: – input of initial data; – setting agents on the search plane; – numbering EPA in the flock; – setting the initial velocity of the EPA and thermal radiation of each EPA; – calculation of the position of each EPA on the total search area and its cost; – approach (attraction) of the EPA to another EPA; – changing in the trajectory of EPA movement; – selection of the best individuals from the EPA flock; – ranking the obtained solutions and sorting them; – training EPA knowledge bases; – determining the amount of necessary computing resources for an intelligent decision support system. The originality of the proposed method lies in setting EPA taking into account the uncertainty of the initial data, improved global and local search procedures taking into account the noise degree of data on the state of the analysis object. The method makes it possible to increase the efficiency of data processing at the level of 13–17 % due to the use of additional improved procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes in the interests of solving national security problems

Development of a solution search method using an advanced flying squirrel algorithm

The object of the study is decision support systems. The subject of the study is the decision-making process in management problems using the flying squirrel algorithm (FSA), an advanced genetic algorithm and evolving artificial neural networks. A solution search method using an advanced FSA is proposed. The study is based on the FSA algorithm for finding a solution regarding the state of an object. Evolving artificial neural networks are used to train FSA, and an advanced genetic algorithm is used to select the best FSA. The method has the following sequence of actions. Input of initial data and setting agents on the search plane take place. After that, numbering FSA in the flock and setting the initial fitness function are carried out. Then, the quality of food in the FSA search area is determined, and the classification of trees (food sources) for FSA is carried out. The next step is the creation of new locations by FSA gliding, formation of the FSA action algorithm in the presence of a predator. After that, the FSA seasonal monitoring conditions are checked, the stop criterion is checked, and new FSA positions are generated taking into account the degree of data noise. The originality of the proposed method lies in setting FSA taking into account the uncertainty of the initial data, advanced global and local search procedures taking into account the noise degree of data on the state of the analysis object. The method makes it possible to increase the efficiency of data processing at the level of 21–25 % due to the use of additional advanced procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes in the interests of solving national security problems

The Development of the Solution Search Method Based on the Improved Bee Colony Algorithm

Active digitization of people's daily life leads to the use of the decision making support systems (DMSS). DMSS is actively used in data processing, forecasting the course of various processes, providing informational support for the decision making process by decision makers. However, a number of problems arise while evaluating monitoring objects, namely: a large number of destabilizing factors affecting the efficiency of the processes of information collection, processing and transmission; high dynamism of changes in the state and composition of heterogeneous monitoring objects during the conduct of hostilities (operations); high dynamism of conducting hostilities (operations); the uncertainty of the initial situation and the noise of the initial data. In this article, a method of finding solutions based on an improved bee colony algorithm was developed. The efficiency of information processing is achieved by learning the architecture of artificial neural networks; taking into account the type of uncertainty of the information to be evaluated; the use of an improved algorithm of the bee colony, the use of an unordered linguistic scale of measurements with adjustment coefficients for the degree of awareness and the degree of noise of the initial data. An approbation of the use of the proposed method was carried out on the example of assessing the state of the operational grouping of troops (forces). The method is proposed to be used in the development of software for automated systems of control of troops and weapons, namely, in the modernization of existing and development of new automated systems of control of troops and weapons. The evaluation of the effectiveness of the proposed method showed an increase in the efficiency of the evaluation at the level of 21–28% in terms of the efficiency of information processing.

Development of a solution search method using an improved locust swarm algorithm

The object of the research is decision support systems. The subject of the research is the decision-making process in management problems using the locust swarm algorithm and evolving artificial neural networks. A solution search method using an improved locust swarm algorithm is proposed. The research is based on the locust swarm algorithm for finding a solution regarding the state of an object. For training locust agents (LA), evolving artificial neural networks are used. The method has the following sequence of steps: – input of initial data; – processing of initial data taking into account the degree of uncertainty; – initial setting of LA in the search area; – determination of the initial speed of the LA movement; – a search vector is generated taking into account the degree of uncertainty; – calculation of the change in the value of the LA fitness function; – training of LA knowledge bases. The originality of the proposed method lies in the arrangement of LA taking into account the uncertainty of the initial data, improved procedures of global and local search taking into account the degree of noise of data about the state of the analysis object. Also, the originality of the research is avoiding the concentration of LA on the current best positions, reducing the probability of premature convergence of the algorithm and maintaining a balance between the convergence rate of the algorithm and diversification. The peculiarity of the proposed method is the use of an improved procedure for LA training. The training procedure consists in learning the parameters and architecture of individual elements and the architecture of the artificial neural network as a whole

Development of a solution search method using an improved monkey algorithm

The object of the research is decision support systems. The subject of the research is the decision-making process in management problems using the monkey algorithm and evolving artificial neural networks. A solution search method using an improved monkey algorithm is proposed. The research is based on the monkey algorithm – for finding a solution regarding the state of an object. For training monkey agents (MA), evolving artificial neural networks are used. The method has the following sequence of steps: – input of initial data; – processing of initial data taking into account the degree of uncertainty; – a search vector is generated for each MA, taking into account the degree of uncertainty; – determination of the initial speed of MA movement; – calculation of the fitness function of the MA solution; – calculation of the height of MA movement; – verification of fulfillment of local jump conditions; – generation of local search plane coordinates; – calculation of the fitness function of the MA solution; – generation of global search plane coordinates; – search distribution among the MA flock; – changing the speed of MA movement; – checking the permissible value of the obtained solution regarding the object state; – training of MA knowledge bases. The originality of the proposed method lies in the arrangement of MA taking into account the uncertainty of the initial data, improved procedures of global and local search taking into account the degree of noise of data about the state of the analysis object. A feature of the proposed method is the use of an improved MA training procedure. The training procedure consists in learning the parameters and architecture of individual elements and the architecture of the artificial neural network as a whole. The method makes it possible to increase the efficiency of data processing at the level of 23–28 % due to the use of additional improved procedures

Condition-based Design of Variable Impedance Controllers from User Demonstrations

This paper presents an approach to ensure conditions on Variable Impedance Controllers through the off-line tuning of the parameters involved in its description. In particular, we prove its application to term modulations defined by a Learning from Demonstration technique. This is performed through the assessment of conditions regarding safety and performance, which encompass heuristics and constraints in the form of Linear Matrix Inequalities. Latter ones allow to define a convex optimisation problem to analyse their fulfilment, and require a polytopic description of the VIC, in this case, obtained from its formulation as a discrete-time Linear Parameter Varying system. With respect to the current state-of-art, this approach only limits the term definition obtained by the Learning from Demonstration technique to be continuous and function of exogenous signals, i.e. external variables to the robot. Therefore, using a solution-search method, the most suitable set of parameters according to assessment criteria can be obtained. Using a 7-DoF KinovaGen3 manipulator, validation and comparison against solutions with relaxed conditions are performed. The method is applied to generate Variable Impedance Controllers for a pulley belt looping task, inspired by the Assembly Challenge for Industrial Robotics in World Robot Summit 2018, to reduce the exerted force with respect to a standard (constant) Impedance Controller. These controllers fulfil a set of safety constraints, namely stability, bounds on task variables and maximum response overshooting; and their performance is determined by the User Preference heuristic, which allows to intuitively define the desired compliant behaviour along the task. In the context of the task, this is used to generate new controllers for one-off modifications of the nominal belt looping task setup without new demonstrations.

Development of a solution search method using an improved fish school algorithm

The object of research is decision support systems. The subject of research is the decision-making process in management problems using the fish school (FSH) algorithm, an advanced genetic algorithm and evolving artificial neural networks. A solution search method using an improved FSH algorithm is proposed. The study is based on the FSH algorithm for finding a solution on the object state. For training FSH, evolving artificial neural networks are used. The method has the following sequence of actions: – input of initial data; – processing of initial data taking into account the degree of uncertainty; – checking the fitness function of the solution found; – procedure of feeding fish agents (FA); – instinctive-collective FA swimming; – calculation of the center of school gravity; – collective voluntary FA swimming; – changing the FA swimming parameters; – training of FA knowledge bases. The originality of the proposed method lies in the arrangement of FA taking into account the uncertainty of the initial data, improved global and local search procedures taking into account the degree of noise of data about the state of the analysis object. The peculiarity of the proposed method is the use of an improved FA training procedure. The training procedure consists in learning the synaptic weights of the artificial neural network, the type and parameters of the membership function, the architecture of individual elements and the architecture of the artificial neural network as a whole. The use of the method makes it possible to increase the efficiency of data processing at the level of 18–25 % due to the use of additional improved procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes in the interest of solving national security problems

The development of solution search method using improved jumping frog algorithm

The object of research is the decision making support systems. The subject of the research is the decision making process in management tasks using an advanced jumping frog algorithm (JFA), an advanced genetic algorithm and evolving artificial neural networks. A method of finding solutions with the use of improved JFA is proposed. The research is based on the JFA to find a solution regarding the object state. Evolving artificial neural networks are used to train frog agents (FA). The method has the following sequence of actions: – an input of initial data; – processing of initial data taking into account the degree of uncertainty; – calculation of the value of the criterion of optimality of each permutation from the initial FA population – global search of FA; – an improvement of the FA position in the search space; – a regulation of the speed of vehicle movement. – an improvement of the working conditions of JFA; – the FA rearrangement; – an unification of all memplexes into one group; – the verification of the fulfillment of the conditions of JFA operation; – the search for the best FA; – training of the FA knowledge bases. The originality of the proposed method consists in the arrangement of the FA taking into account the uncertainty of the initial data, the improved procedures of global and local edge taking into account the degree of data noise about the analysis object state, the adjustment of the degree of data noise during the FA movement, the adjustment of the speed of the FA movement. Also, the peculiarity of the proposed method is the use of an improved procedure for FA training. The use of the method makes it possible to increase the efficiency of data processing at the level of 14–18 % due to the use of additional improved procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes in the interests of solving national security problems

A Desirability-Based Solution Search Method for Sequential Optimization of the Hot Rolling Process

Abstract Although it is an old technique, research on the hot rolling process maintains its importance because of its widespread usage in steel production and its requirement for a vast amount of resources, especially energy. The roll pass design of the hot rolling process considerably affects many operational parameters such as energy requirement, roll wear, working forces, and torques. Furthermore, due to the sequential nature of the rolling process, a design of any number of passes is closely interrelated with all other passes in the process. This complexity makes it challenging to find optimal design solutions that strike a balance between conflicting goals and constraints. In this article, a new optimized solution search strategy based on a desirability function is offered to address the sequential characteristics of the roll pass design. A novel optimization method utilizing response surfaces and the proposed solution search strategy is presented to reduce the shaping energy of the overall process while minimizing turning moments and radial forces on rolls during the rough rolling process. The proposed method provides integrated optimization of the process by ensuring information flow between the passes and can also be applied to other sequential processes with some modifications. The developed method and solution search strategy are illustrated and validated through a case study. The findings of the case study are compared to three distinct pass designs used in industrial power plants. The results show significant energy savings, lower turning moments, and reduced radial forces compared to the reference designs.

Development of the solution search method using the population algorithm of global search optimization

The research objects are decision making support systems. subject research is a decision making process in management tasks using bio-inspired algorithms. A method of finding solutions using the population algorithm of global search optimization is proposed. Joint use of invasive weed algorithm is proposed, genetic algorithm and evolving artificial neural networks are improved. The method has the following sequence of actions: ‒ an input of initial data; ‒ processing of initial data taking into account the degree of uncertainty; ‒ formation of the optimization vector; ‒ creation of descendant vectors; ‒ ordering of vectors in descending order; ‒ reducing the dimensionality of the feature space; ‒ teaching knowledge bases. The peculiarity of the proposed method lies in the placement of agents-weeds, taking into account the uncertainty of the initial data, improved procedures for reducing the space of signs about the analysis object state. Training of synaptic weights of an artificial neural network, type and parameters of the membership function and the architecture of individual elements, and the architecture of an artificial neural network as a whole is carried out. The proposed method was simulated in the MathСad 14 software environment. The task to be solved during the simulation was to determine the route of the ships in the operational zones of the Black and Azov seas in the conditions of hybrid actions of the enemy. The use of the method makes it possible to increase the efficiency of data processing at the level of 21–27 % due to the use of additional improved procedures. The proposed method should be used to solve the problems of evaluating complex and dynamic processes in the interests of solving national security problems

Improvement of the solution search method based on the cuckoo algorithm

An improved method of finding solutions based on the cuckoo algorithm is proposed. The research object is the decision-making support systems. The research subject is the decision making process in management tasks using artificial intelligence methods. The hypothesis of the research is to increase the efficiency of decision making with a given assessment reliability. The proposed method is based on a combination of the cuckoo algorithm and evolving artificial neural networks. The method has the following differences: ‒ an additional processing of the source data takes place taking into account the uncertainty about the state of the control objects and the type of data noise about the state of the control object is additionally taken into account; ‒ the state model of the control object is adjusted taking into account the available computing resources of the system; ‒ added procedures to reduce the probability of detecting nests and reducing the length of the cuckoo’s step; ‒ knowledge bases about management objects are additionally taught. The training procedure consists in learning the synaptic weights of the artificial neural network, the type and parameters of the membership function and the architecture of individual elements and the architecture of the artificial neural network as a whole. The effectiveness of the proposed method was evaluated and it was established that the proposed modification provides a better value of the objective function compared to the results obtained by other authors and ensures the fulfillment of all restrictions. The specified example showed an increase in the efficiency of data processing at the level of 21–28 % due to the use of additional improved procedures. It is advisable to use the proposed method in decision making support systems of automated control systems.

Multi-Objective Deep Network-Based Estimation of Distribution Algorithm for Music Composition

In the field of evolutionary algorithm music composition, most of the current researches focus on how to enhance environmental selection based on multi-objective evolutionary algorithms (MOEAs). However, the real music composition process defined as large-scale multi-optimization problems (LSMOP) involve the number of combinations, and the existing MOEA-based optimization process can be challenging to effectively explore the search space. To address this issue, we propose a new Multi-Objective Generative Deep network-based Estimation of Distribution Algorithm (MODEDA) based on dimensionality reduction in decision space. In order to alleviate the difficulties with dimensional transformation, we propose a novel solution search method that optimizes in the transformed space and ensures consistency between the pareto sets of the original problem. The proposed algorithm is tested on the knapsack problems and music composition experiments. The experimental results have demonstrated that the proposed algorithm has excellency in terms of its optimization performance and computational efficiency in LSMOP.

Metaheuristics for the permutation flowshop problem with a weighted quadratic tardiness objective

In this paper, we consider a permutation flowshop problem, with a weighted squared tardiness objective function, which addresses an important criterion for many customers. Our objective is to find metaheuristics that can, within acceptable computational times, provide sizeable improvements in solution quality over the best existing procedure (a dispatching rule followed by an improvement method).We consider four metaheuristics, namely iterated local search (ILS), iterated greedy (IG), variable greedy (VG) and steady-state genetic algorithms (SSGA). These are known for performing well on permutation flowshops and/or on tardiness criteria. For each metaheuristic, four versions are developed, differing on the choice of initial sequence and/or local search. Additionally, four different time limits are considered. Therefore, a total of 64 sets of results are obtained.The results show that all procedures greatly outperform the best existing method. The IG procedures provide the best results, followed by the SSGA procedures. The VG methods are usually inferior to SSGA, while the ILS metaheuristics tend to be the worst performers.The four metaheuristics prove to be robust in what regards initial solution and local search method, since both have little effect on the performance of the metaheuristics. Increasing the time limit does improve the performance of all procedures. Still, a sizeable improvement is obtained even for the lowest time limit. Therefore, even under restrictive time limits, the metaheuristics greatly outperform the best existing procedure.

Fractional Brownian motion inference of multivariate stochastic differential equations

Recently, the financial mathematics has been emerged to interpret and predict the underlying mechanism that generates an incident of concern. A system of differential equations can reveal a dynamical development of financial mechanism across time. Multivariate wiener process represents the stochastic term in a system of stochastic differential equations (SDE). The standard wiener process follows a Markov chain, and hence it is a martingale (kind of Markov chain), which is a good integrator. Though, the fractional Wiener process does not follow a Markov chain, hence it is not a good integrator. This problem will produce an Arbitrage (non-equilibrium in the market) in the predicted series. It is undesired property that leads to erroneous conclusion, as it is not possible to build a mathematical model, which represents the financial phenomenon. If there is Arbitrage (unbalance) in the market, this can be solved by Wick-Ito-Skorohod stochastic integral (renormalized integral). This paper considers the estimation of a system of fractional stochastic differential equations (FSDE) using maximum likelihood method, although it is time consuming. However, it provides estimates with desirable characteristic with the most important consistency. Langevin method can be used to find the mathematical form of the functions of stochastic differential equations. This includes drift and diffusion by estimating conditional mean and variance from the data and finding the suitable function achieves the least error, and then estimating the parameters of the model by numerical optimal solution search method. Data used in this paper consist of three banking sector stock prices including Baghdad Bank (BBOB), the Commercial Bank (BCOI), and the National Bank (BNOI).

Numerical analysis of membrane–absorption separation for supercritical carbon dioxide and water mixture of plume geothermal power generation systems

A plume geothermal system provides a viable option for simultaneously storing carbon dioxide and producing supercritical working fluid with geothermal energy. Its water content, however, may cause problems, such as water hammer and corrosion, when the geothermal energy is utilized. A membrane–absorption separation method is employed to remove water from the supercritical carbon dioxide–water mixture. A numerical solution procedure is thereafter employed to evaluate the separation performance with different design parameters. If it is assumed that each membrane is repeatable and independent, then it can be divided into regular hexagon structures. The results show that a lower mixture inlet velocity and a higher lithium bromide solution concentration lead to a better separation performance. Moreover, the membrane remains practically unchanged even when the mixture inlet temperature varies. A multi-objective genetic algorithm optimization is implemented with an optimal solution search method. For a 65% concentration lithium bromide solution, the optimization results indicate that the best separation efficiency can reach 93.53%, and the total mass transfer area is 1093.5 m2. The findings suggest that membrane–absorption separation is efficient and commercially viable for separating supercritical carbon dioxide–water mixtures. This separation technology can provide purified working fluids for power generation systems.

Principles for Development of Predictive Stability Models of Social and Economic Systems on the basis of DTW

This paper presents the concept for the development of predictive models of social and economic system evolution providing the necessity of combining solution search optimization algorithms and methods of regressive and clustering analysis for the adequate description of system attribute space. The rationale for the selection of metrics on the basis of a dynamic time-warping algorithm which allows to carry out clustering of the system attribute space. The example of solution of description task for COVID-19 pandemic development attribute for a particular country or region is considered. The developed concept formulates main provisions and indicators that can be used in order to increase the algorithm efficiency for the development of predictive complicated system models.

Randomness as source for inspiring solution search methods: Music based approaches

As the world progresses towards industrialization, engineering problems become increasingly complex and it becomes even more difficult to optimize these problems. The reason for this is the increasing complexity of variables, dimensions, space complexity, and time complexity. In order to be able to cope with such a situation, randomized intelligent optimization and search algorithms are proposed to optimize numerical benchmarking problems, multi-objective problems, and solve difficult problems including a large number of variables, dimensions, constraints, and objectives. Metaheuristic random search and optimization methods are widely used to search and find the most appropriate solutions for large-scale optimization problems in an acceptable time. They are general-purposed methods that can be efficiently applied to optimization and search problems without too much modification to accommodate a specific probing. Metaheuristic optimization algorithms are generally categorized as physics, music, sociology, biology, swarm, mathematics, plant, chemistry, sports, water, and hybrid based. Although most of the intelligent metaheuristic methods are inspired by physics and biology; concepts, activities, rules, and processes in music can be an inspiration source of new intelligent optimization and search techniques. That is why; novel and efficient music inspired intelligent optimization and search methods having effective exploitation and exploration capabilities have been proposed.In this paper, music based metaheuristic optimization algorithms were gathered and analyzed for the first time. Harmony search and its versions, melody search algorithm, and method of musical composition have been examined in detail. Furthermore, their performances have been compared within both unconstrained numerical benchmark functions and constrained problems and the obtained results from music based algorithms have been comparatively studied.

A non-revisiting quantum-behaved particle swarm optimization based multilevel thresholding for image segmentation

Multilevel thresholding for image segmentation is one of the crucial techniques in image processing. Even though numerous methods have been proposed in literature, it is still a challenge for the existing methods to produce steady satisfactory thresholds at manageable computational cost in segmenting images with various unknown properties. In this paper, a non-revisiting quantum-behaved particle swarm optimization (NrQPSO) algorithm is proposed to find the optimal multilevel thresholds for gray-level images. The proposed NrQPSO uses the non-revisiting scheme to avoid the re-evaluation of the evaluated solution candidates. To reduce the unnecessary computation cost, the NrQPSO provides an automatic stopping mechanism which is capable of gauging the progress of exploration and stops the algorithm rationally in a natural manner. For further improving the computation efficiency, the NrQPSO employs a meticulous solution search method to overcome the drawback of the existing QPSO algorithms using the original search methods. Performance of the NrQPSO is tested on the Berkeley segmentation data set. The experimental results have demonstrated that the NrQPSO can outperform the other state-of-the-art population-based thresholding methods in terms of efficiency, effectiveness and robustness; thus, the NrQPSO can be applied in real-time massive image processing.