Effects of finite register length on fast ICA, bacterial foraging optimization based ICA and constrained genetic algorithm based ICA algorithm

Acharya, Debiprasad Priyabrata; Panda, Ganapati; Lakshmi, Y. V. S.

doi:10.1016/j.dsp.2009.08.012

Cited by 21 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bu aşamanın amacı, bağımsız bileşenlerin çıkarımını basitleştirmektir. Bu işlemlerden sonra gerekli olan bileşenler çıkarılır [23][24][25][26].…”

Section: A Kullanılan Bba Yöntemleriunclassified

AQDD Özelliklerine BBA Yöntemleri Uygulanarak Parkinson Hastalığının Otomatik Teşhisi

Yücelbaş

2019

Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

z-Parkinson hastalığı dopamin üreten beyin hücrelerinin kaybı sonucunda oluşan bir hastalıktır. Bu hastalığın birçok teşhis yöntemi bulunmakta olup ses sinyallerinin analizi de bunlardan birisidir. Bu çalışmada daha önceden 188 Parkinson hastası ve 64 sağlıklı olmak üzere toplam 252 kişiye ait kaydedilmiş ses sinyallerinden ayarlanabilir Q-faktör dalgacık dönüşümü (AQDD) metodu kullanılarak elde edilen özellikler kullanılmıştır. Bu özelliklere bağımsız bileşen analizi (BBA) çeşitlerinden olan hızlı BBA (HBBA), max-kurtosis BBA (KBBA) ve yeniden yapılanma BBA (YBBA) olmak üzere üç farklı özellik azaltma (boyut indirgeme) yöntemi uygulanmıştır. Bu işlemler sonucunda minimum özellik sayısıyla maksimum başarı oranı elde edilmeye çalışılmıştır. Bu amaçla, öncelikle yeni özellikler ile oluşturulan veri grubuna ayrı ayrı k-kat çapraz doğrulama yöntemi uygulanarak veriler eğitim-test olarak ayrılmıştır. Sonraki aşamada, hazırlanan veriler rastgele orman (RO) algoritması ile sınıflandırılmış ve sonuçlar çeşitli istatistiksel ölçütlerle yorumlanmıştır. Sonuçlar değerlendirildiğinde; kullanılan boyut indirgeme yöntemleri içerisinde en başarılı yöntem %82.01 sınıflandırma doğruluk oranı ve yaklaşık 0.85 ROC ve PRC değerleri ile YBBA olmuştur. Bu durum hasta ve sağlıklı sınıf ayrışımının mükemmele yaklaştığını kanıtlamıştır. Gerçek yaşam uygulamalarına uygun olan bu çalışmanın performans sonuçları ve kullanılan veri sayısının yüksek oluşu çalışmanın literatürdeki önemini ortaya koymaktadır. Ayrıca, çalışma kapsamında kullanılan özellik indirgeme yöntemlerinin analizi, bu alanda yapılabilecek çalışmalara yol gösterebilecek niteliktedir. Anahtar Kelimeler-Parkinson Hastalığı, Ses Sinyali Analizi, Boyut İndirgeme Metotları, AQDDbstract-Parkinson's disease is occurred due to loss of brain cells which are releasing dopamine. There are many different techniques to diagnosis of this disease and analysis of audio signals is one of them. In this study, the features obtained by using the tunable Q-factor wavelet transform (TQWT) method from the previously recorded audio signals of 252 subjects (188 of data belongs to Parkinson's disease and the others are healthy). Three different feature reduction (size reduction) methods such as fast ICA (FICA), max-kurtosis ICA (KICA) and reconstruction ICA (RICA), which are independent component analysis (ICA), were applied to these properties. We aimed to obtain maximum success rate with minimum number of features using these operations. To do this, firstly the k-fold cross validation method was applied to the data group created with new features and was split into training and test group. The data, then, was classified with random forest (RO) algorithm and the results were evaluated with various statistical criteria. It was concluded that RICA with 82.01% classification accuracy rate and approximately 0.85 ROC and PRC values are most successful method among the size reduction methods. This result showed that patient and healthy class separation is approaching excellence. The performance results o...

show abstract

“…Bu aşamanın amacı, bağımsız bileşenlerin çıkarımını basitleştirmektir. Bu işlemlerden sonra gerekli olan bileşenler çıkarılır [23][24][25][26].…”

Section: A Kullanılan Bba Yöntemleriunclassified

AQDD Özelliklerine BBA Yöntemleri Uygulanarak Parkinson Hastalığının Otomatik Teşhisi

Yücelbaş

2019

Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

show abstract

“…Aiming at the shortcoming of ICA, Acharya et al proposed a constrained genetic algorithm (GA) optimization based on independent component analysis [6]. But GA has some disadvantages such as an inclination to becoming premature and low efficiency.…”

Section: Introductionmentioning

confidence: 99%

An Improved Particle Swarm Optimization Application to Independent Component Analysis

Nian

Sun

et al. 2009

2009 International Conference on Information Engineering and Computer Science

View full text Add to dashboard Cite

The traditional searching scheme of independent component analysis (ICA) is based on gradient algorithm. And a learning step size is required beforehand. It couldn't resolve the problem of convergence. To overcome the drawback, an improved particle swarm optimization (PSO) is applied to ICA algorithm. Firstly, the dynamic inertia weight which is based on evolution speed and aggregation degree is introduced into PSO. And then, Based on the analysis of ICA, a fitness function of PSO was defined. Finally, the detailed algorithm was given by using improved PSO. Based on TIMIT corpus and Noise-92 database, the experiments were implemented. The results indicate that the performance of DPSO-ICA algorithm is superior to the traditional FastICA for processing mixed noisy speech signals.

show abstract

“…GA has been applied to ICA problem in [15], [16], [17], [18], [19] for more than ten years, resulting in two main methods constrained genetic algorithm based ICA (CGAICA) [15], [17] and Bacterial foraging optimization based ICA (BFOICA). The constrained GA based ICA (CGAICA) has been proposed in [20] which estimates all the ICs and resolves the permutation indeterminacy.…”

Section: Introductionmentioning

confidence: 99%

Independent component analysis based on genetic algorithms

Wen

Zhang

Lin

et al. 2014

2014 10th International Conference on Natural Computation (ICNC)

View full text Add to dashboard Cite

FastICA and Infomax are the most popular algorithms for calculating independent components. These two optimization process usually lead to unstable results. To overcome this drawback, a genetic algorithm for independent component analysis has been developed with enhancement of the independence of the resulting components. By modifying the FastICA to start from given initial point and adopting a new feasible fitness function, the original target of obtaining the maximum mutual independence is achieved. The proposed method is evaluated and tested on a numerical simulative data set from the measures of the normalized mutual information, negentropy and kurtosis, together with the accuracy of the estimated components and mixing vectors. Experimental results on simulated data demonstrate that compared to FastICA and Infomax, the proposed algorithm can give more accurate results together with stronger independence.

show abstract

Effects of finite register length on fast ICA, bacterial foraging optimization based ICA and constrained genetic algorithm based ICA algorithm

Cited by 21 publications

References 16 publications

AQDD Özelliklerine BBA Yöntemleri Uygulanarak Parkinson Hastalığının Otomatik Teşhisi

AQDD Özelliklerine BBA Yöntemleri Uygulanarak Parkinson Hastalığının Otomatik Teşhisi

An Improved Particle Swarm Optimization Application to Independent Component Analysis

Independent component analysis based on genetic algorithms

Contact Info

Product

Resources

About