A biomedical system based on fuzzy discrete hidden Markov model for the diagnosis of the brain diseases

Uğuz, Harun; Öztürk, Ali; Saraçoğlu, Rıdvan; Arslan, Ahmet

doi:10.1016/j.eswa.2007.08.006

Cited by 18 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning [9], is used to predict, examining, distinct (RHI) [10], [11]. In this article, initial describe the model for necessary intra-organ, molecular interaction, medium [12], i.e., action potential-based cardio molecular interaction medium.…”

Section: Introductionmentioning

confidence: 99%

Notice of Retraction: Molecular Diagnostic and Using Deep Learning Techniques for Predict Functional Recovery of Patients Treated of Cardiovascular Disease

et al. 2019

View full text Add to dashboard Cite

Today, with the development of industry and mechanized life style, the prevalence of the disease is rising steadily as well. Observing at the trend and lifecycle style, its predict that after ten years around 23.6 million people die because of Cardiovascular Disease (CVD). For that reason, aim to use Deep Learning Techniques (DLTs), to analysis stable CVD that would give valuable awareness to decrease misdiagnosis in the Robust Healthcare Industry (RHI). An objective of this paper is first, Molecular diagnosis (MD), and second using Deep Learning Techniques DLTs, to synthesis and characterize to accumulate (raw information) from CVD patients, those who admitted the emergency section between January (2018 to December 2019). We are using Artificial Neural Network (ANN), model characterize to predict CVD patients and configuration, Feature selection (FS), Mean Square Error (MSE), accuracy, sensitivity. The ANN accuracy is 98.4, K-nearest neighbor (KNN) accuracy is 98.01%, Naïve Bayes (NB), accuracy is 96.99%. Decision tree (DT), accuracy is 87.81%. Our robust data driven model explore the efficient accuracy rate to predict CVD patients. The ANN model in term of their efficient in disease analysis, and prognosis of the RHI. INDEX TERMS Artificial neural network (ANN), cardiovascular disease (CVD), molecular diagnostic (MD), Robust Healthcare Industry (RHI).

show abstract

Section: Introductionmentioning

confidence: 99%

Notice of Retraction: Molecular Diagnostic and Using Deep Learning Techniques for Predict Functional Recovery of Patients Treated of Cardiovascular Disease

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Discrete Hidden Markov Model (DHMM) has been widely applied in automatic speech recognition (Digalakis, Tsakalidis, Harizakis, & Neumeyer, 2000;Nwe, Foo, & De Silva, 2003), gesture recognition (Chen, Fu, & Huang, 2003;Gao, Fanga, Zhao, & Chen, 2004;Kim, Song, & Kim, 2007), character recognition (Dehghan, Faez, Ahmadi, & Shridhar, 2001;Khorsheed, 2003;Premaratne, Järpe, & Bigun, 2006), fault diagnosis (Tai, Ching, & Chan, 2009), and medical diagnosis systems (Uguz, Arslan, Saraçoglu, & Türkoglu, 2008a, 2008b. The fundamental theory of hidden Markov models (HMMs) were put forward by Baum and his colleagues at the end of the 1960s (Baum & Egon, 1967;Baum & Petrie, 1970;Baum, 1972).…”

Section: Introductionmentioning

confidence: 98%

“…In this fuzzy approach, an observation belongs to each cluster with a specific membership value. Thus, different observations will not have the same observation probability and information loss will decrease (Uguz, Öztürk, Saraçoglu, & Arslan, 2008b).…”

Section: Introductionmentioning

confidence: 99%

Classification of internal carotid artery Doppler signals using fuzzy discrete hidden Markov model

Uğuz¹,

Kodaz²

2011

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

“…The proposed method clearly overcame their results using the five cameras (camera5 gives the worst results), and learning from the first sequence. Moreover, in Section II we have mentioned FDHMM [36] which is able to train a stable HMM from a single sequence of vectors in a unit simplex, as our proposal does. However, the histogram distribution is not considered and therefore it fails in the experiments as shown in Table II where we conduct the FDHMM experiments with and without the MAP adaptation.…”

Section: B Strict One-shot Learningmentioning

confidence: 99%

“…Previous work has shown how a HMM modification called Fuzzy Discrete HMM (FDHMM) exploits a soft-assignment in a discrete HMM [36], obtaining a stable training with scarce data. Its application in activity recognition improves the performance [8] in a relaxed one-shot learning scenario, and the method can benefit from a Transfer Learning process [9].…”

Section: Related Workmentioning

confidence: 99%

One-Shot Learning of Human Activity With an MAP Adapted GMM and Simplex-HMM

Rodriguez

Orrite

Medrano

et al. 2017

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Abstract-This paper presents a novel activity class representation using a single sequence for training. The contribution of this representation lays on the ability to train an one-shot learning recognition system, useful in new scenarios where capturing and labelling sequences is expensive or impractical. The method uses a Universal Background Model of local descriptors obtained from source databases available on-line and adapts it to a new sequence in the target scenario through a Maximum a Posteriori adaptation. Each activity sample is encoded in a sequence of normalized Bag of Features and modelled by a new Hidden Markov Model formulation, where the EM algorithm for training is modified to deal with observations consisting in vectors in a unit simplex. Extensive experiments in recognition have been performed using one-shot learning over the public datasets Weizmann, KTH and IXMAS. These experiments demonstrate the discriminative properties of the representation and the validity of application in recognition systems, achieving state-of-the-art results.

show abstract

A biomedical system based on fuzzy discrete hidden Markov model for the diagnosis of the brain diseases

Cited by 18 publications

References 20 publications

Notice of Retraction: Molecular Diagnostic and Using Deep Learning Techniques for Predict Functional Recovery of Patients Treated of Cardiovascular Disease

Notice of Retraction: Molecular Diagnostic and Using Deep Learning Techniques for Predict Functional Recovery of Patients Treated of Cardiovascular Disease

Classification of internal carotid artery Doppler signals using fuzzy discrete hidden Markov model

One-Shot Learning of Human Activity With an MAP Adapted GMM and Simplex-HMM

Contact Info

Product

Resources

About