Similarity-Based Fuzzy Classification of ECG and Capnogram Signals

2016

Automatika

Self Cite

Original scientific paperTraditionally, supervised machine learning methods are the first choice for tasks involving classification of data. This study provides a non-conventional hybrid alternative technique (pEAC) that blends the Possibilistic Fuzzy CMeans (PFCM) as base cluster generating algorithm into the 'standard' Evidence Accumulation Clustering (EAC) clustering method. The PFCM coalesces the separate properties of the Possibilistic C-Means (PCM) and Fuzzy C-Means (FCM) algorithms into a sophisticated clustering algorithm. Notwithstanding the tremendous capabilities offered by this hybrid technique, in terms of structure, it resembles the hEAC and fEAC ensemble clustering techniques that are realised by integrating the K-Means and FCM clustering algorithms into the EAC technique. To validate the new technique's effectiveness, its performance on both synthetic and real medical datasets was evaluated alongside individual runs of well-known clustering methods, other unsupervised ensemble clustering techniques and some supervised machine learning methods. Our results show that the proposed pEAC technique outperformed the individual runs of the clustering methods and other unsupervised ensemble techniques in terms accuracy for the diagnosis of hepatitis, cardiovascular, breast cancer, and diabetes ailments that were used in the experiments. Remarkably, compared alongside selected supervised machine learning classification models, our proposed pEAC ensemble technique exhibits better diagnosing accuracy for the two breast cancer datasets that were used, which suggests that even at the cost of none labelling of data, the proposed technique offers efficient medical data classification.Key words: Evidence accumulation clustering, K-means, fuzzy C-means, possibilitic fuzzy C-means, hybrid intelligent systems, health informatics, medical data classification, disease diagnosis.Grupiranje zasnovano na skupljanju dokaza s vjerojatnosno-neizrazitim C-means pristupom za dijagnozu bolesti. Tradicionalno, metode nadziranog strojnog učenja predstavljaju prvi izbor za zadatke koji uključuju klasifikaciju podataka. Ovo istraživanje prikazuje nekonvencionalnu hibridnu alternativnu (pEAC) tehniku koja kombinira vjerojatnosno-neizraziti C-Means (PFCM) kao osnovni algoritam grupiranja u standardno grupiranje korištenjem grupiranja zasnovanog na skupljanju dokaza (EAC). PFCM objedinjuje zasebna svojstva vjerojatnosnog C-Means (PCM) i neizrazitog C-Means (FCM) algoritama u sofisticirani algoritam grupiranja. Usprkos ogromnim mogućnostima koje nudi ova tehnika, u smislu strukture, ona je nalik cjelovitim hEAC i fEAC tehnikama grupiranja realiziranim integracijom K-Means i FCM algoritama grupiranja u EAC tehniku. Kako bi se validirala učinkovi-tost, njeno ponašanje je ispitano na sintetičkim i stvarnim medicinskim podacima te su provedene usporedbe s pojedinačnim široko rasprostranjenim metodama, drugim nenadziranim tehnikama grupiranja i nekim nadziranim metodama učenja. Rezultat prikazuje kako predložena pEAC tehnika nadmašuje poje...

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evidence Accumulation Clustering with Possibilitic Fuzzy C-Means base clustering approach to disease diagnosis

2016

Automatika

Self Cite

“…Electroencephalogram (EEG) and electrocardiogram (ECG) signals are usually used in diagnosing the diseases such as epileptic seizure, schizophrenia, asthma, and arrhythmia [2][3][4][5][6][7]. Such uses in [2][3][4][5][6] focus on epileptic seizure detection, schizophrenia detection and Alzheimer based on EEG signals.…”

Section: Introductionmentioning

confidence: 99%

A Combined AdaBoost and NEWFM Technique for Medical Data Classification

Lecture Notes in Electrical Engineering

2015

Self Cite

Abstract.A hybrid technique combining the AdaBoost ensemble method with the neural network with fuzzy membership function (NEWFM) method is proposed for medical data classification and disease diagnosis. Combining the Adaboost, a general method used to improve the performance of learning methods, with the 'standard' NEWFM, which uses as base classifiers, ensures better accuracy in medical data classification tasks and diagnosis of diseases. To validate the proposal, four medical datasets related to epileptic seizure detection, Parkinson, cardiovascular (heart), and hepatitis disease diagnoses were used. The results show an average classification accuracy of 95.8% (made up of best accuracy of 99.5% for epileptic seizure, 87.9% for Parkinson, 97.4% for cardiovascular (heart) disease, and 98.7% for Hepatitis dataset classifications), which suggests that the proposed technique is capable of efficient medical data classification and potential applications in disease diagnosis and treatment.

“…Epileptic seizures in epilepsy patients are known to affect sensory and motor functions; awareness; emotional state; memory; or behavior [1]. Biomedical signals are usually measured in regular time intervals and they repeat similar complexities cyclically [2]. The electroencephalogram (EEG) signal is one of such biomedical signal samples.…”

Section: Introductionmentioning

confidence: 99%

Principal component analysis-based neural network with fuzzy membership function for epileptic seizure detection

2014 10th International Conference on Natural Computation (ICNC)

Suciati

et al. 2014

Self Cite

A hybrid principal component analysis (PCA)-based neural network with fuzzy membership function (NEWFM) is proposed for epileptic seizure detection. By combining PCA and NEWFM, the proposed method improves the accuracy in epileptic seizure detection. The PCA is used for wavelet feature enhancement needed to eliminate the sensitivity of noise, electrode artifacts, or redundancy. NEWFM, a model of neural networks, is integrated to improve prediction results by updating weights of fuzzy membership functions. A dataset made up of 5 sets, each consisting 100 single EEGs segments, is employed to evaluate the proposed system's performance. Based on the experiments, the prediction results show an accuracy rate of 98.29% for epileptic seizure classification while in the best cases the accuracy reaches 99.5% for the 'normal' (Z-S) seizure classification task.