Data Mining - Concepts and Techniques.

Ensemble methods are considered the state‐of‐the art solution for many machine learning challenges. Such methods improve the predictive performance of a single model by training multiple models and combining their predictions. This paper introduce the concept of ensemble learning, reviews traditional, novel and state‐of‐the‐art ensemble methods and discusses current challenges and trends in the field.

Ensemble learning: A survey

Introduction to stochastic programming

Feature selection is an important task in data mining and machine learning to reduce the dimensionality of the data and increase the performance of an algorithm, such as a classification algorithm. However, feature selection is a challenging task due mainly to the large search space. A variety of methods have been applied to solve feature selection problems, where evolutionary computation (EC) techniques have recently gained much attention and shown some success. However, there are no comprehensive guidelines on the strengths and weaknesses of alternative approaches. This leads to a disjointed and fragmented field with ultimately lost opportunities for improving performance and successful applications. This paper presents a comprehensive survey of the state-of-the-art work on EC for feature selection, which identifies the contributions of these different algorithms. In addition, current issues and challenges are also discussed to identify promising areas for future research.

/pdf/a-survey-on-evolutionary-computation-approaches-to-feature-5c2qznm5vr.pdf

A Survey on Evolutionary Computation Approaches to Feature Selection

C4.5: Programs for Machine Learning (書評)

Minimization of maximum lateness on parallel machines with sequence-dependent setup times and job release dates

The multi-objective reentrant hybrid flowshop scheduling problem (RHFSP) exhibits significance in many industrial applications, but appears under-studied in the literature. In this study, an iterated Pareto greedy (IPG) algorithm is proposed to solve a RHFSP with the bi-objective of minimising makespan and total tardiness. The performance of the proposed IPG algorithm is evaluated by comparing its solutions to existing meta-heuristic algorithms on the same benchmark problem set. Experimental results show that the proposed IPG algorithm significantly outperforms the best available algorithms in terms of the convergence to optimal solutions, the diversity of solutions and the dominance of solutions. The statistical analysis manifestly shows that the proposed IPG algorithm can serve as a new benchmark approach for future research on this extremely challenging scheduling problem.

Bi-objective reentrant hybrid flowshop scheduling: an iterated Pareto greedy algorithm

A sequential exchange approach for minimizing earliness–tardiness penalties of single-machine scheduling with a common due date

Metaheuristics for scheduling a non-permutation flowline manufacturing cell with sequence dependent family setup times

Case-based reasoning (CBR), a popular problem solving methodology in data mining, solves new problems by analyzing solutions for similar past problems. The many advantages of CBR include rapid learning, the ability to use numerous unrestricted domains, minimal knowledge requirements, and effective presentation of knowledge. However, a major difficulty when applying CBR algorithms is selection of appropriate parameter values, features and weight assignment of features, to avoid constructing poor models. Unfortunately, key CBR parameters, beneficial features and the weight assignment of features vary across different problems. This study developed an efficient CBR approach based on artificial immune system algorithm (AISCBR) to increase classification accuracy by improving parameter tuning, feature selection and weight assignment of features. The proposed approach was then compared with those of other studies using the same University of California, Irvine (UCI) data sets. The experimental results showed that the AISCBR can provide better performance than other existing methods, because higher classification accurate rates can be obtained.

Shih-Wei Lin

Papers

Minimization of maximum lateness on parallel machines with sequence-dependent setup times and job release dates

Bi-objective reentrant hybrid flowshop scheduling: an iterated Pareto greedy algorithm

A sequential exchange approach for minimizing earliness–tardiness penalties of single-machine scheduling with a common due date

Metaheuristics for scheduling a non-permutation flowline manufacturing cell with sequence dependent family setup times

Parameter tuning, feature selection and weight assignment of features for case-based reasoning by artificial immune system