A new fuzzy classifier based on simulated annealing and subtractive clustering

Setting a compact and accurate rule base constitutes the principal objective in designing fuzzy rule-based classifiers. In this regard, the authors propose a designing scheme based on the combination of the subtractive clustering (SC) and the particle swarm optimization (PSO). The main idea relies on the application of the SC on each class separately and with a different radius in order to generate regions that are more accurate, and to represent each region by a fuzzy rule. However, the number of rules is then affected by the radiuses, which are the main preset parameters of the SC. The PSO is therefore used to define the optimal radiuses. To get good compromise accuracy-compactness, the authors propose using a multi-objective function for the PSO. The performances of the proposed method are tested on well-known data sets and compared with several state-of-the-art methods.

Download Full-text

An Efficient Method for Extracting Fuzzy Classification Rules from High Dimensional Data

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.1997.p0031 ◽

1997 ◽

Vol 1 (1) ◽

pp. 31-36 ◽

Cited By ~ 11

Author(s):

Stephen L. Chin ◽

Keyword(s):

Efficient Method ◽

High Dimensional Data ◽

Estimation Method ◽

Feature Space ◽

Fuzzy Classification ◽

High Dimensional ◽

Subtractive Clustering ◽

Classification Rules ◽

Fuzzy Classifier ◽

Aerospace Applications

We present an efficient method for extracting fuzzy classification rules from high dimensional data. A cluster estimation method called subtractive clustering is used to efficiently extract rules from a high dimensional feature space. A complementary search method can quickly identify the important input features from the resultant high dimensional fuzzy classifier, and thus provides the ability to quickly generate a simpler, more robust fuzzy classifier that uses a minimal number of input features. These methods are illustrated through the benchmark iris data and through two aerospace applications.

Download Full-text

Penjadwalan Produksi Menggunakan Metode Simulated Annealing pada Unit Produksi Daun Pintu di PT. ML

Talenta Conference Series Energy and Engineering (EE) ◽

10.32734/ee.v2i2.445 ◽

2019 ◽

Vol 2 (2) ◽

Author(s):

Rosnani Ginting ◽

Chairul Rahmadsyah Manik

Keyword(s):

Simulated Annealing ◽

Problem Solving ◽

Production Scheduling ◽

Production Control ◽

Delivery Time ◽

Production Schedule ◽

A Company ◽

Predetermined Time ◽

Factory Floor

Penjadwalan merupakan aspek yang sangat penting karena didalamnya terdapat elemen perencanaan dan pengendalian produksi bagi suatu perusahaan yang dapat mengirim barang sesuai dengan waktu yang telah ditentukan, untuk memperoleh waktu total penyelesaian yang minimum. Masalah utama yang dihadapi oleh PT. ML adalah keterlambatan penyelesaian order yang mempengaruhi delivery time ke tangan costumer karena pelaksanaan penjadwalan produksi dilantai pabrik belum menghasilkan makespan yang sesuai dengan order yang ada. Oleh kaena itu dituntut untuk mencari solusi pemecahan masalah optimal dalam penentuan jadwal produksi untuk meminimisasi total waktu penyelessaian (makespan) semua order. Dalam penelitian ini, penjadwalan menggunakan metode Simulated Annealing (SA) diharapkan dapat menghasilkan waktu total penyelesaian lebih cepat dari penjadwalan yang ada pada perusahaan. Scheduling is a very important aspect because in it there are elements of planning and production control for a company that can send goods in accordance with a predetermined time, to obtain a minimum total time of completion. The main problem faced by PT. ML is the delay in completing orders that affect delivery time to customer because the implementation of production scheduling on the factory floor has not produced the makespan that matches the existing order. Therefore, it is required to find optimal problem solving solutions in determining the production schedule to minimize the total time of elimination (makespan) of all orders. In this study, scheduling using the Simulated Annealing (SA) method is expected to produce a total time of completion faster than the existing scheduling in the company.

Download Full-text