Autosoft Journal

Online Manuscript Access



Listing 88 manuscripts matching the search of "genetic algorithm"

Genetic Algorithm and Tabu Search Memory with Course Sandwiching (GATS_CS) for University Examination Timetabling

by Abayomi-Alli Adebayo, Sanjay Misra, Luis Fernández-Sanz, Abayomi-Alli Olusola

Abstract: Educational Institutions use timetables to maximize and optimize scarce resources like time and space when scheduling classes, lectures, examinations or events. This makes University timetable scheduling a complicated constraint problem. This study aims to develop an examination timetable system for a University to solve the problems associated with the present manual technique such as un-allocation of courses, course clashes, course duplication, multiple examinations per hall, elongated and laborious reviews, etc. The hybrid of meta-heuristics procedures: Genetic Algorithm (GA) and Tabu Search (TS) memory was employed along with course sandwiching (GATS_CS) to develop an improved automatic University examination timetable solution. For implementation, a case study of a public University in Nigeria was used. The concepts of Genetic Algorithm: Selection, Evaluation were implemented while memory properties of TS and course sandwiching was used to replaced genetic operators of Crossover and Mutation. Course allocation and hall scheduling was optimized based on defined constraints for the case study University while GAT_CS was implemented in Java. Result obtained showed that GAT_CS allocated 96.07% and 99.02% of the total courses to exam halls, un-allocated 3.93% and 0.98% for first and second semesters, respectively. Also, in several instances it automatically sandwiched (scheduled) multiple examinations into a single hall without exceeding the hall's exam sitting capacity. GAT_CS also outperformed Particle Swarm Optimization and Local Search (PSO_LS) and Generic Algorithm (GA) based timetable implementations when benchmarked with the same timetable dataset. The system could be improved to reduce clashes, duplication, multiple examinations and accommodate more system defined constraints for future directions.

Online Article

Performance Analyses of Nature-inspired Algorithms on the Traveling Salesman’s Problems for Strategic Management

by Julius Beneoluchi Odili, Mohd Nizam Mohmad Kahar, A. Noraziah, M. Zarina, Riaz Ul Haq

This paper carries out a performance analysis of major Nature-inspired Algorithms in solving the benchmark symmetric and asymmetric Traveling Salesman’s Problems (TSP). Knowledge of the workings of the TSP is very useful in strategic management as it provides useful guidance to planners. After critical assessments of the performances of eleven algorithms consisting of two heuristics (Randomized Insertion Algorithm and the Honey Bee Mating Optimization for the Travelling Salesman’s Problem), two trajectory algorithms (Simulated Annealing and Evolutionary Simulated Annealing) and seven population-based optimization algorithms (Genetic Algorithm, Artificial Bee Colony, African Buffalo Optimization, Bat Algorithm, Particle Swarm Optimization, Ant Colony Optimization and Firefly Algorithm) in solving the 60 popular and complex benchmark symmetric Travelling Salesman’s optimization problems out of the total 118 as well as all the 18 asymmetric Travelling Salesman’s Problems test cases available in TSPLIB91. The study reveals that the African Buffalo Optimization and the Ant Colony Optimization are the best in solving the symmetric TSP, which is similar to intelligence gathering channel in the strategic management of big organizations, while the Randomized Insertion Algorithm holds the best promise in asymmetric TSP instances akin to strategic information exchange channels in strategic management.

Volume: 24, Issue: 4

A Review on Artificial Intelligence Methodologies for the Forecasting of Crude Oil Price

by Haruna Chiroma, Sameem Abdul-kareem, Ahmad Shukri Mohd Noor, Adamu Abubakar, Nader Sohrabi Safa, Liyana Shuib, Mukhtar Fatihu Hamza, Abdulsalam Yau Gital, Tutut Herawan

When crude oil prices began to escalate in the 1970s, conventional methods were the predominant methods used in forecasting oil pricing. These methods can no longer be used to tackle the nonlinear, chaotic, non-stationary, volatile, and complex nature of crude oil prices, because of the methods2019 linearity. To address the methodological limitations, computational intelligence techniques and more recently, hybrid intelligent systems have been deployed. In this paper, we present an extensive review of the existing research that has been conducted on applications of computational intelligence algorithms to crude oil price forecasting. Analysis and synthesis of published research in this domain, limitations and strengths of existing studies are provided. This paper finds that conventional methods are still relevant in the domain of crude oil price forecasting and the integration of wavelet analysis and computational intelligence techniques is attracting unprecedented interest from scholars in the domain of crude oil price forecasting. We intend for researchers to use this review as a starting point for further advancement, as well as an exploration of other techniques that have received little or no attention from researchers. Energy demand and supply projection can effectively be tackled with accurate forecasting of crude oil price, which can create stability in the oil market.

Volume: 22, Issue: 3

Perception-Based Software Release Planning

by Mubarak Alrashoud, Abdolreza Abhari

Release planning is a cornerstone of incremental software development. This paper proposes a novel framework that performs the prioritization aspect of the software release-planning process. The aim of this framework is to help software product managers to select the most promising requirements that will be implemented in the next release. Many variables affect release planning, including: The importance of requirements as perceived by the different stakeholders; decision weights of the stakeholders; the risk associated with each requirement as estimated by the development team; the effort needed to implement each requirement; the release size (the effort allocated to implement and deliver a software release); and the dependencies among requirements. We assume that there are no ambiguities in defining the dependencies among requirements. Also it is assumed that the estimation of the available effort is accurate. Because of human perception, such variables as importance, risk, and required effort have a high degree of imprecision and uncertainty. Therefore, the strength and practicality of the Fuzzy Inference System (FIS) is employed to manipulate uncertainty in these three factors. In order to reflect the disagreements among the stakeholders on the FIS engine, the polling method is used to define the parameters of the membership functions of the importance variable. The effectiveness of the proposed framework is compared to genetic algorithm approach, which is applied in many works in the literature. The results of this comparison show that the proposed FIS-based approach achieves higher degree of stakeholders0027 satisfaction than genetic algorithm-based approach.

Volume: 21, Issue: 2

A Heuristic Field Navigation Approach for Autonomous Underwater Vehicles

by Hui Miao, Xiaodi Huang

As an effective path planning approach, Potential Field Method has been widely used for Autonomous Underwater Vehicles (AUVs) in underwater probing projects. However, the complexity of the realistic environments (e.g. the three dimensional environments rather than two dimensional environments, and limitations of the sensors in AUVs) have limited most of the current potential field approaches, in which the approaches can only be adapted to theoretic environments such as 2D or static environments. A novel heuristic potential field approach (HPF) incorporating a heuristic obstacle avoidance method is proposed in this paper for AUVs path planning in three dimensional environments which have dynamic targets. The contributions of this paper are: (1) The approach is able to provide solutions for more realistic and difficult conditions (such as three dimensional unknown environments and dynamic targets) rather than hypothetic environments (flat 2D known static environments); (2) The approach results in less computation time while giving better trade-offs among simplicity, far-field accuracy, and computational cost. The performance of the HPF is compared with previous published Simulated Annealing (SA) and Genetic Algorithm (GA) based methods. They are analyzed in several environments. The performance of the heuristic potential field approach is demonstrated through case studies not only to be effective in obtaining the optimal solution but also to be more efficient in processing time for dynamic path planning.

Volume: 20, Issue: 1

Cost-Efficient Environmentally-Friendly Control of Micro-Grids Using Intelligent Decision-Making for Storage Energy Management

by Y. S. MANJILI, Rolando Vega, Prof Mo Jamshidi

A smart decision-making framework based on genetic algorithms (GA) and fuzzy logic is proposed for control and energy management of micro-grids. Objectives are to meet the demand profile, minimize electricity consumption cost, and to modify air pollution under a dynamic electricity pricing policy. The energy demand in the micro-grid network is provided by distributed renewable energy generation (coupling solar and wind), battery storage and balancing power from the electric utility. The fuzzy intelligent approach allows the calculation of the energy exchange rate of the micro-grid storage unit as a function of time. Such exchange rate (or decision-making capability) is based on (1) the electrical energy price per kilowatt-hour (kWh), (2) local demand (load), (3) electricity generation rate of renewable resources (supply), and (4) air pollution measure, all of which are sampled at predefined rates. Then, a cost function is defined as the net dollar amount corresponding to electricity flow between micro-grid and the utility grid. To define the cost function one must consider the cost incurred by the owner of the micro-grid associated to its distribution losses, in addition to its demand and supply costs, in such a way that a positive cost translates to owner losses and a negative cost is a gain. Six likely scenarios were defined to consider different micro-grid configurations accounting for the conditions seen in micro-grids today and also the conditions to be seen in the future. GA is implemented as a heuristic (DNA-based) search algorithm to determine the sub-optimal settings of the fuzzy controller. The aforementioned net cost (which includes pricing, demand and supply measures) and air pollution measures are then compared in every scenario with the objective to identify best-practices for energy control and management of micro-grids. Performance of the proposed GA-fuzzy intelligent approach is illustrated by numerical examples, and the capabilities and flexibility of the proposed framework as a tool for solving intermittent multi-objective function problems are presented in detail. Micro-grid owners looking into adopting a smart decision-making tool for energy storage management may see an ROI between 5 and 10.

Volume: 19, Issue: 4

FDA Performance Analysis of Job Shop Schedule in Uniform Parallel Machines

by Jin Chen, Yufeng Deng, Xueming He

The challenging problem of a non-homogeneous machine load planning is to distribute jobs to the different machines with the same ability at the operation for the minimum cost. Each operation can be performed by a set of machines with the same or different characters, and each machine can handle a job many times with different operations. A new heuristics method (FDA, Four Dimension Algorithm) for uniform parallel machine scheduling is proposed in this paper to tackle this load distribution problem. The FDA method is to select a sequence, a machine set and an operation such that the minimum evaluation of the defined indexes is achieved. These indexes consist of four independent parameters. Essentially, this method consists of three main iteratives in implementation: iterative for job numbers, iterative for the operation turns and iterative for the non-homogeneous machines. Each operation is associated with a set of evaluation indexes. The proposed algorithm has shown a significant improvement over Genetic Algorithm and Branch and Bound Algorithm. The key of this new method is partial indexes calculated in every cycle only. As a result, the complexity of this method is greatly improved from exponential to only polynomial (O(mnplus3m2n2) at most). The most noticeable innovation in this proposed method is the practical efficient algorithm capable of analyzing non-homogeneous machine and job relations while reducing complexity of computation. Of equal importance, a various examples and experiments are shown in detail.

Volume: 19, Issue: 4

Recycling Plants Layout Design by Means of an Interactive Genetic Algorithm

by Laura Garcia-Hernandez, Antonio Arauzo-Azofra, Lorenzo Salas-Morera, Henri Pierreval, Emilio Corchado

Facility Layout Design is known to be very important for attaining production efficiency because it directly influences manufacturing costs, lead times, work in process and productivity. Facility Layout problems have been addressed using several approaches. Unfortunately, these approaches only take into account quantitative criteria. However, there are qualitative preferences referred to the knowledge and experience of the designer, which should also be considered in facility layout design. These preferences can be subjective, not known in advance and changed during the design process, so that, it is difficult to include them using a classic optimization approach. For that reason, we propose the use of an Interactive Genetic Algorithm (IGA) for designing the layout of two real recycling plants taking into consideration subjective features from the designer. The designers knowledge guides the evolution of the algorithm evaluating facility layouts in each generation adjusting the search to his/her preferences. To avoid the fatigue of the designer, he/she evaluates only the most representative individuals of the population selected through a soft computing clustering method. The algorithm is applied on two real world waste recycling plant layout problems: a carton packs recycling plant and chopped plastic one. The results are compared with another method, proving that the new approach is able to capture the designer preferences in a reasonable number of iterations.

Volume: 19, Issue: 3

Job Allocation And Scheduling In Multi Robotic Tasks Considering Collision Free Operation

by Chang Park, Gi-Nam Wang

This paper presents a method of job allocation and scheduling that determines optimal job allocation and the shortest paths for robots having collision regions. The problem described in this paper is an application of a classical flexible job-shop scheduling problem with shared resources. A genetic algorithm and a TABU search are used for the job allocation and scheduling procedures. Overlapping activities in a collision region can result in robot collisions. This should be a hard constraint in which a non-overlapping condition is guazanteed. To achieve this, the sequencing in a collision region should be determined. Job assignrnents, ordering in non-collision regions of each robot, and priorities in regions shazed between various robots are encoded using a genetic representation in which the objective is to minimize the job completion time. As the seazch space is extremely large, a genetic algorithm is used for global searches and TABU is used for local searches. The most viable solution is obtained using the genetic algorithm. The TABU search enhances the solution by changing the path order of each robot in non-collision regions as well as the priorities in regions shared by various robots. A genetic encoding method and a procedure to calculate the makespan value under non-collision constraints was developed. To use the TABU search, neighborhoods were developed to boost the local search capability. As a verification test, the proposed method was applied to real problems in the automobile industry.

Volume: 15, Issue: 2

Fuzzy Approach to Portfolio Selection Using Genetic Algorithms

by Rashad Aliev, Rahib Abiyev, Mustafa Menekay

The portfolio construction problem usually has been viewed in the framework of risk-return trade-off. Using deterministic and stochastic portfolio models used to solve the problem lead to unrealistic results as both the expected return rate and the risk are vague. Moreover, the decision maker frequently deals with insufficient data when selecting a portfolio. Using fuzzy models allows removal of these drawbacks and permits the incorporation of the expert knowledge. However, the existing fuzzy portfolio selection models aze mainly oriented to partial fuzzification of deterministic linear programming models (mainly modeling uncertainty in the return) without the incorporation of fuzzy risk. These models do not always allow effective management of the conflict between expected return and risk. They also suffer from high computational complexity resulting from the use of the classical fuzzy linear programming approach. In this paper we propose a fuzzy portfolio selection model based on fuzzy linear programming solved by genetic algorithm that provides for fmding a global near-optimal solution with a reduction in computational complexity compazed to the existing methods. The proposed model takes into account fuzzy expected return and investor’s fuzzy risk preference and gives chance of possibility trade-off between risk and return. This is obtained by assigning degree of satisfaction between criteria and constraints and defining tolerance for the constraints in order to obtain the goal value in the objective risk function. Experimental results demonstrate high efficiency of the proposed method.

Volume: 14, Issue: 4

A Fast Scalable Evolutionary Algorithm for the QoS Multicast Routing Problem

by S. Al-Sharhan, F. Karray, W. Gueaieb

The increasing demand of real-time multimedia services makes of quality of service based routing a serious challenge for next-generation networks. The complexity of this NP-complete problem significantly increases with the size of the network. A new evolutionazybased multicast routing algorithm is presented in this paper. It is based on computational intelligence techniques that integrate in an efficient manner the merits of genetic algorithms and the concepts of competitive leazning in the area of artificial neural networks. Population-based incremental learning algorithm is utilized, among other techniques, to construct a delay bounded multicast tree. The proposed algorithm is capable of simultaneously satisfying several key quality of service requirements that aze necessazy for real-time multimedia applications. The main objective of the algorithm is to construct a multicast tree that is characterized by a minimum cost and a bounded end-to-end delay and residual bandwidth. It is shown through a series of extensive experimental studies that the proposed algorithm outperforms several other popular heuristic based routing algorithms in terms of execution time as well as the quality of the generated solution, for various network sizes, multicast tree sizes, and delay bounds. It is also shown that the performance of the algorithm becomes significantly superior to others as the network size increases, which confirms its high scalability.

Volume: 14, Issue: 4

A New Utilization of the Hamiltonian Formalism in the Adaptive Control of Mechanical Systems Under External Perturbation

by J.K. Tar, I.J. Rudas, J.F. Bitoacute, O.M. Kaynak

A novel approach toward the adaptive control of robots dynamically interacting with an unmodeled environment and having only approximately known dynamic parameters has been developed on the basis of the principles of the Hamiltonian Mechanics. As the different means of modern Soft Computing technology having a more or less uniform architecture independent of the particular details of the problems to be solved by them, the proposed method also has a uniform structure not strictly tailored to the peculiar properties of the mechanical system to be controlled. However, as special kinds of Artificial Neural Networks (ANN) are fit to solve wide but typical classes of tasks, the proposed method is invented for tackling problems related to the control of mechanical devices in which the dominating non-linear coupling originates from the laws of Classical Mechanics. As ANNs have a plenty of free parameters (connection weights and threshold values) the tuning of which means learning, this mechanical model also contains tunable parameters so offering the possibility of learning. In this paper the modelaposs free parameters, possible constraints imposed on them as well as different tuning strategies are compared to each other on the basis of computer simulations. It is concluded that the method based on the canonical formalism of classical mechanics is promising for gaining different solutions to the problem. However, finding the appropriate tuning rule is far not trivial and a wide area is open for further research from this point of view. The simple tuning strategies here investigated serve as basic paradigms open for further development in the direction of more conventional and better understood methods as Genetic Algorithms or other ldquoEvolutionary Computationrdquo approach.

Volume: 5, Issue: 4


ISSN PRINT: 1079-8587
ISSN ONLINE: 2326-005X
DOI PREFIX: 10.31209
10.1080/10798587 with T&F
IMPACT FACTOR: 0.652 (2017/2018)

SJR: "The two years line is equivalent to journal impact factor ™ (Thomson Reuters) metric."

Journal: 1995-Present


TSI Press
18015 Bullis Hill
San Antonio, TX 78258 USA
PH: 210 479 1022
FAX: 210 479 1048