Projek ini berhubungkait dengan perbandingan antara dua teknik pengurangan dimensi sesuatu set data. Dua teknik yang terlibat ialah Principal Component Analysis sebagai teknik yang umum diaplikasikan manakala Random Projection merupakan teknik yang baru diperkenalkan. Kajian adalah berdasarkan keputusan daripada dua kawalan neural iaitu Standard Backpropagation dan Fuzzy ARTMAP. Data piawaian dan data pesakit digunakan dalam kajian ini. Keputusan daripada dua kawalan neural dikira berdasarkan percentage of correct classification, purity, and collective entropy. Pengujian hipotesis iaitu ujian t dilaksanakan untuk menguji perbezaan min antara dua min populasi berdasarkan sample yang terhasil daripada keputusan kawalan neural untuk Principal Component Analysis dan Random Projection. Keputusan yang sah berdasarkan pengujian hipotesis pada ralat, α = 0.05 ataupun selang keyakinan 95%, dihasilkan dan ini menyumbang kepada kesimpulan yang kukuh dalam membuat perbandingan antara dua teknik pegurangan dimensi ini. Keputusan daripada data pesakit juga membuktikan Random Projection boleh diaplikasikan secara praktikal. Di samping itu, Random Projection juga meghasilkan keputusan yang setara berbanding Principal Component Analysis. Satu perbincangan disertakan untuk menerangkan keputusan yang diperolehi dan kesimpulan dibuat untuk kajian ini. Cadangan disertakan di akhir disertasi ini untuk perkembangan dan kajian pada masa hadapan untuk teknik pengurangan dimensi.
_________________________________________________________________________________________
project involves an analysis of the effectiveness of two dimensionality reduction techniques, i.e., Principal Component Analysis as the standard approach and Random Projection as a recent technique. The study is based on the performance of two supervised neural network classifiers i.e., Standard Backpropagation and Fuzzy ARTMAP. A set of benchmark and real medical databases are used to evaluate the performance of the neural network models. The performance indicators used are percentage of correct classification, purity, and collective entropy. The Student’s two-tailed paired t-test is used to compare the significance of differences of the results. Based on the estimated 95% confidence intervals, a strong decision which eventually leads to a convincing conclusion on the performance of the dimensionality reduction techniques can be obtained. The perceived experimental results especially from the real medical data sets are encouraging enough to prove that Random Projection exhibits good performance as a dimensionality reduction technique. Surprisingly, Random Projection is effective on low dimensional data, and the outcomes are as good as Principal Component Analysis. A discussion on generalization of the results obtained is included, and a conclusion ensues. Recommendations are also included for further improvements and enhancements in the analysis of dimensionality reduction techniques.
An analysis of two dimensionality reduction techniques on the performance of neural network classifiers_Ong Siok Lan_E3_2005_NI