Research Notes

July 4, 2014: a posting on Minimum Message Length (MML) is posted today. It is a point estimation and model selection principle which accommodates the Bayesian Theory and the Information Theory in conducting the process.

February 23, 2014: a posting on Analytical Hierarchy Process (AHP) is posted today. It is a method usually used for developing a Decision Support Systems, which includes the use of data and user preferences.

September 20, 2011: a posting on Document Clustering Algorithm is posted today, continuing a post on Document Clustering that has been posted before.

April 25, 2011: a posting on Image Clustering is posted today. As a part of implementation of clustering to a problem, this posting is useful to people who want to apply Data Mining to real world problems.

September 8, 2010: a note on Hash Function is posted today. A concern about using a good data structure in speeding up a program application as well as a thought of using this as a base of clustering process.

July 17, 2010: a simple note on Single Pass Clustering is posted today. A type of clustering which groups data into its closest one by simply comparing the distance of it to each cluster.

March 19, 2010: a simple note on Genetic Algorithm is posted today. A simple note to keep the track of understanding in regards to optimisation problem.

February 11, 2010: a simple and very brief note on Bayesian Networks is posted today. Hope of any use.

December 4, 2009: I put a bibliography (clustering bibliography) of references that I have usually used for my writing on clustering. The bibliography will be updated when new related references are found.

November 25, 2009: in the end, all papers presented in National Conference on Systems and Informatics are listed in this blog. The page can be accessed via KNS&I page.

November 10, 2009: an explanation on Simulated Annealing was posted. The searching method is a popular one and often used for solving optimization problems.

November 02, 2009: a short note on Latent Class Analysis was posted as a note on the subject. Relation to other methods is also noted.

October 05, 2009: a short note on Algoritma Rock was posted to provide a brief look at the alternative procedure in performing clustering. Some notes are also pointed at the end of the writing.

September 07, 2009: a short note on Locality Sensitive Hashing was posted as a reminder of the use of the method and its relation to other methods.

August 11, 2009: a note in regards to internship students from France working on Mining All Frequent Queries which is very useful in building a data warehouse.

July 29, 2009: a note about Latent Class Cluster Analysis (LCCA) which is the same as Mixture Model method for continuous variable, has been posted today. Hope of any use.

January 13, 2009: a note about Feature Selection which is useful in preprocessing datasets, has been posted today. Hope of any use.

October 09, 2008: a note about Artificial Neural Networks has been posted today. Hope of any use.

September 22, 2008: SNOB is a mixture modelling program for modelling data unsupervisedly. SNOB is a bit different from other mixture programs.

August 04, 2008: A short description of a type of data mining methods: Association Rules was posted today.

July 24, 2008: An explanation of a representation of document used in a document clustering process i.e. Document Clustering was posted today.

July 16, 2008: A short explanation of a type of supervised classification method i.e. Decision Trees was posted today.

June 25, 2008: An explanation of another representation or model of sequence data i.e. Hidden Markov Model was added today.

June 24, 2008: An brief explanation about sequence clustering was added today.

June 24, 2008: Markov Chain, a type of method used for sequence analysis was added today.

June 12, 2008: A note on a type of clustering: Quality Threshold Clustering, which is usually used for clustering gene, was posted today.

June 09, 2008: A note of Wavelet Transform: the extention form of Fourier Transform and Short Term Fourier Transform for handling non-stationary signals with a different window function was posted today.

June 02, 2008: A continuation note of Fourier Transform on Short Term Fourier Transform: the form of Fourier Transform for handling non-stationary signals was posted today.

May 30, 2008: A posted on Fourier Transform might be useful for you and me as a short note.

May 21, 2008: I have posted a note on the discussion we had at SC-INA mailing list regarding this year’s first e-collocium (Voronoi Based Coverage Control with Anisotropic Sensor).

May 15, 2008: I added a short description about K Harmony Means which is a variance of K-Means and X-Means which is a method for finding the number of clusters into My K-Means Clustering Page.

May 14, 2008: A posting on Clustering on Categorical Data might be useful. In relation to that, I have also updated my K-Means page with the K-Modes method which can also be used for clustering categorical data.

May 13, 2008: A note on Similarity Measure is posted today. The measures are useful for performing clustering.

May 09, 2008: A short explanation about the application of the Expectation Maximisation (EM) algorithm to Mixture Modelling was added into My Mixture Modelling page.

May 07, 2008: A short explanation about the Expectation Maximisation (EM) algorithm was posted today. This algorithm is commonly used to find Maximum Likelihood (ML) solution of a probabilistic model.

April 30, 2008: I added a short description about Kernel K-Means to My K-Means Clustering Page.

April 30, 2008: A Note on Support Vector Machine will hopefully give you (and me) a preliminary understanding of the method.

April 28, 2008: A description of a variance of k-means which is the fuzzy c-means method was added into the page of K-Means Clustering.

April 21, 2008: A short description of two clustering validity criteria (Elbow criterion and Gaussian Means criterion) in learning k in k-means were added into the page of K-Means Clustering.

April 15, 2008: I have started a k-means clustering page containing a brief explanation of the clustering method. Please have a look at my K-Means Clustering Page.

April 11, 2008: This page is probably useful for you who have interest in conducting research: TIPS: Mencari Artikel Ilmiah Gratis.

April 08, 2008: Literature review looks simple, but it is not quite. Please have a look at my note on TIPS: Pembuatan Literature Review.

April 03, 2008: I wrote a note on Naive Bayes. Another method for classification based on Bayesian Theory.

March 27, 2008: Based on the discussion we had at indo-dm mailing list, I put a note on kNN Algorithm.

March 19, 2008: I have started a mixture modelling page containing a brief definition of the thing. Please have a look at my Mixture Modelling Page.

March 17, 2008: There will be interns coming from France and will be developing a system on Rule Mining For Relational Database.

March 11, 2008: A girl from Riau asked me about modelling accuracy when using k-means. I then put a note on Akurasi Hasil Pemodelan K-Means. The method explained here is often referred to as Bootstrapped Method.

March 03, 2008: I have started a clustering page containing some clustering methods including k-means, mixture modelling, hierarchical clustering, Self-Organising Map (SOM) and some other related materials. Please have a look at my Mixture Modelling Page.