Pawel B. Myszkowski

Hybrid ant colony optimization in solving multi-skill resource-constrained project scheduling problem

In this paper, hybrid ant colony optimization (HAntCO) approach in solving multi-skill resource-constrained project scheduling problem (MS-RCPSP) has been presented. We have proposed hybrid approach that links classical heuristic priority rules for project scheduling with ant colony optimization (ACO). Furthermore, a novel approach for updating pheromone value has been proposed based on both the best and worst solutions stored by ants. The objective of this paper is to research the usability and robustness of ACO and its hybrids with priority rules in solving MS-RCPSP. Experiments have been performed using artificially created dataset instances based on real-world ones. We published those instances that can be used as a benchmark. Presented results show that ACO-based hybrid method is an efficient approach. More directed search process by hybrids makes this approach more stable and provides mostly better results than classical ACO.

Evolutionary algorithm in Forex trade strategy generation

This paper shows an evolutionary algorithm application to generate profitable strategies to trade futures contracts on foreign exchange market (Forex). Strategy model in approach is based on two decision trees, responsible for taking the decisions of opening long or short positions on Euro/US Dollar currency pair. Trees take into consideration only technical analysis indicators, which are connected by logic operators to identify border values of these indicators for taking profitable decision(s). We have tested the efficiency of presented approach on learning and test time-frames of various characteristics.

Learning Assistant - Personalizing Learning Paths in e-Learning Environments

The paper presents an agent called Learning Assistant, which is responsible for defining individual learning paths for pupils in e-learning environment. The Assistant is able to infer using metadata described pupils and didactic materials; this inference is a basis for building the individual learning path for each pupil. To build a learning path for a new pupil the agent uses information collected during introductory tests. A SOM neural network is used for grouping similar pupils. WebTeacher is e-learning environment in which Learning Assistant works. This environment is shortly presented in the paper. Next, we present the idea of personalization-we consider the individuals pupil characteristic and a group of similar pupils characteristic. Data structures described didactic materials and pupils are also shortly explained. The performed experiments allow formulate some conclusions, they are described very shortly. Summary ends the paper.

Data Mining Techniques in e-Learning CelGrid System

The paper presents e-learning an system as a source of large datasets that can be analyzed by data mining techniques. Proposed data mining techniques can be used as a didactic content recommendation system, feedback tool, intrusion detection tools etc. All techniques are applied to make learning process more effective (taking into account time consuming aspects and resource usage). The paper describes data mining tasks and techniques that can be applied to CelGrid system. A particular attention is given to the active learning paradigm as an e-learning system is mostly a source of unlabeled data.

Solving Scheduling Problems by Evolutionary Algorithms for Graph Coloring Problem

This chapter presents a new evolutionary approach to the Graph Coloring Problem (GCP) as a generalization of some scheduling problems: timetabling, scheduling, multiprocessor scheduling task and other assignment problems. The proposed evolutionary approach to the Graph Coloring Problem utilizes information about the conflict localization in a given coloring. In this context a partial fitness function (pff) and its usage to specialize genetic operators (IBIS and BCX) and phenotypic measure of diversity in population are described. The particular attention is given to the practical usage of GCP. The performance of the proposed algorithm is verified by computer experiments on the set of benchmark graphs instances (DIMACS). Additional experiments were done on benchmark graph for timetabling problem.

A new benchmark dataset for Multi-Skill Resource-Constrained Project Scheduling Problem

In this paper novel project scheduling difficulty estimations are proposed for Multi-Skill Resource-Constrained Project Scheduling Problem (MS-RCPSP). The main goal of introducing the complexity estimations is an attempt of estimation the project complexity before launching the optimization process. What is more, the dataset instance generator is also presented as a tool to create new instances for extending the research area. Furthermore, the dataset proposed in previous works is extended by new instances, described thoroughly and released as a benchmark dataset. The dataset instances are also scheduled using simple heuristic and greedy algorithm in duration- and cost- oriented optimization modes. Finally, a brief summary of investigated methods and potential further research directions is presented.

Metaheuristics for tuning model parameters in two natural language processing applications

Choosing model parameters is an important issue for solving real word problems. Wrong parameter values result in low performance of employed model. Usually, parameters are chosen manual, but one can employ metaheuristics for searching the parameter space in more systematic and automated way. In this paper we test a few optimisation methods such as Evolutionary Algorithms, Tabu Search, Hill Climbing and Simulated Annealing for setting parameters of models in two problems in the domain of Natural Language Processing. Metaheuristics used significantly improve performance in comparison to the default parameter selected manually by domain experts.

Hybrid Differential Evolution and Greedy Algorithm (DEGR) for solving Multi-Skill Resource-Constrained Project Scheduling Problem

Abstract Paper presents a hybrid Differential Evolution and Greedy Algorithm (DEGR) applied to solve Multi-Skill Resource-Constrained Project Scheduling Problem. The specialized indirect representation and transformation of solution space from discrete (typical for this problem), to continuous (typical for DE-approaches) are proposed and examined. Furthermore, Taguchi Design of Experiments method has been used to adjust parameters for investigated method to reduce the procedure of experiments. Finally, various initialisation, clone elimination, mutation and crossover operators have been applied there. The results have been compared with the results from other reference methods (HantCO, GRASP and multiStart Greedy) using the benchmark iMOPSE dataset. This comparison shows that DEGR effort is very robust and effective. For 28 instances of iMOPSE dataset DEGR has achieved the best-known solutions.

Trading rule discovery on Warsaw Stock Exchange using revolutionary algorithms

This paper presents an application of coevolutionary algorithms to rule discovery on stock market. We used genetic programming techniques with coevolution in financial data mining process. There were tested a various approaches to include coevolution aspects in task of build trading rule (buy and sell decision). Trading rules are based on technical and fundamental indicators included in decision tree and were tested on Warsaw Stock Exchange historical data.

Efficient selection operators in NSGA-II for solving bi-objective multi-skill resource-constrained project scheduling problem

This paper presents multiple variances of selection operator used in Non-dominated Sorting Genetic Algorithm II applied to solving Bi-Objective Multi-Skill Resource Constrained Project Scheduling Problem. A hybrid Differential Evolution with Greedy Algorithm has been proven to work very well on the researched problem and so it is used to probe the multi-objective solution space. It is then determined whether a multi-objective approach can outperform single-objective approaches in finding potential Pareto Fronts. Additional modified selection operators and a clone prevention method have been introduced and experiments have shown the increase in efficiency caused by their utilization.