Combining Multiple Artificial Neural Networks Using Random Committee to Decide upon Electrical Disturbance Classification

Lira, Milde M. S.; Aquino, Ronaldo R. B. de; Ferreira, Aida A.; Carvalho, Mário de Faria; Neto, Otoni Nobrega; Santos, Gabriela Carvalho Jurema

doi:10.1109/ijcnn.2007.4371414

Cited by 19 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As briefly summarized in Section I-B, available approaches for segmentation of fat and muscle for thigh MRI can be categorized under boundary based methods [11], region based methods such as Markov random field (MRF) [33], graph-cut [34] and clustering [35], and machine learning based methods such as random (decision) forest (RF) [36], multilayer perceptron (MLP) [37], SVM [38], BayesNET [39], Hoeffding trees [40], Random committee [41], and AdaBoost [42]. We compare our proposed method with several existing methods both qualitatively and quantitatively.…”

Section: Comparison To Other Methodsmentioning

confidence: 99%

“…We compare our proposed method with several existing methods both qualitatively and quantitatively. Table III lists the quantitative comparisons of the proposed method's DSCs for fat and muscle segmentation with Boykov's graph-cut [34], active contour [11], [12] and machine learning based methods of random forest [36] and random committee [41].…”

Section: Comparison To Other Methodsmentioning

confidence: 99%

“…First is a lack of software algorithms that can work efficiently and accurately. This is because many algorithms fail to provide exact quantification, and [38], BayesNET in (c) [39], Hoeffding tree in (d) [40], Random committee in (e) [41], Random forest in (f) [36], AdaBoost in (g) [42] and Multilayer perceptron in (h) [37] are trained separately and optimized results are used for comparison with respect to the proposed algorithm (i). The selected MRI slice was used to qualitatively illustrate the impact of image inhomogeneity and fat tissue distribution on segmentation accuracy of each algorithm; the proposed approach (i) shows a dramatic improvement (no over-or under-segmentation issue observed) compared to all other methods.…”

Section: G Quantification From a Single Image Slicementioning

confidence: 99%

See 2 more Smart Citations

A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation

Irmakci

Hussein

Savran

et al. 2019

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is the non-invasive modality of choice for body tissue composition analysis due to its excellent soft tissue contrast and lack of ionizing radiation. However, quantification of body composition requires an accurate segmentation of fat, muscle and other tissues from MR images, which remains a challenging goal due to the intensity overlap between them. In this study, we propose a fully automated, data-driven image segmentation platform that addresses multiple difficulties in segmenting MR images such as varying inhomogeneity, non-standardness, and noise, while producing high-quality definition of different tissues. In contrast to most approaches in the literature, we perform segmentation operation by combining three different MRI contrasts and a novel segmentation tool which takes into account variability in the data. The proposed system, based on a novel affinity definition within the fuzzy connectivity (FC) image segmentation family, prevents the need for user intervention and reparametrization of the segmentation algorithms. In order to make the whole system fully automated, we adapt an affinity propagation clustering algorithm to roughly identify tissue regions and image background. We perform a thorough evaluation of the proposed algorithm's individual steps as well as comparison with several approaches from the literature for the main application of muscle/fat separation. Furthermore, whole-body tissue composition and brain tissue delineation were conducted to show the generalization ability of the proposed system. This new automated platform outperforms other state-of-the-art segmentation approaches both in accuracy and efficiency.

show abstract

Section: Comparison To Other Methodsmentioning

confidence: 99%

Section: Comparison To Other Methodsmentioning

confidence: 99%

Section: G Quantification From a Single Image Slicementioning

confidence: 99%

See 1 more Smart Citation

A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation

Irmakci

Hussein

Savran

et al. 2019

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…An optimal hyperplane is defined as the linear decision function with maximal margin between the vectors of the two classes (Figure 2). Random Committee (RC) [32] is a committee of random classifiers. The base randomizable classifiers (that form the committee members) are built using different random number seeds based in the same data.…”

Section: Classifiersmentioning

confidence: 99%

Histogram-Based Descriptor Subset Selection for Visual Recognition of Industrial Parts

et al. 2020

View full text Add to dashboard Cite

This article deals with the 2D image-based recognition of industrial parts. Methods based on histograms are well known and widely used, but it is hard to find the best combination of histograms, most distinctive for instance, for each situation and without a high user expertise. We proposed a descriptor subset selection technique that automatically selects the most appropriate descriptor combination, and that outperforms approach involving single descriptors. We have considered both backward and forward mechanisms. Furthermore, to recognize the industrial parts a supervised classification is used with the global descriptors as predictors. Several class approaches are compared. Given our application, the best results are obtained with the Support Vector Machine with a combination of descriptors increasing the F1 by 0.031 with respect to the best descriptor alone.

show abstract

“…Each base classifier is constructed using a different random number seed. The final prediction results are a simple average of the results estimated by each base classifier [7].…”

Section: Classificationmentioning

confidence: 99%

Automatic Detection of Sleep Stages based on Accelerometer Signals from a Wristband

Yeo¹,

Koo²,

Park³

2017

IEIE Transactions on Smart Processing and Computing

View full text Add to dashboard Cite

Abstract:In this paper, we suggest an automated sleep scoring method using machine learning algorithms on accelerometer data from a wristband device. For an experiment, 36 subjects slept for about eight hours while polysomnography (PSG) data and accelerometer data were simultaneously recorded. After the experiments, the recorded signals from the subjects were preprocessed, and significant features for sleep stages were extracted. The extracted features were classified into each sleep stage using five machine learning algorithms. For validation of our approach, the obtained results were compared with PSG scoring results evaluated by sleep clinicians. Both accuracy and specificity yielded over 90 percent, and sensitivity was between 50 and 80 percent. In order to investigate the relevance between features and PSG scoring results, information gains were calculated. As a result, the features that had the lowest and highest information gain were skewness and band energy, respectively. In conclusion, the sleep stages were classified using the top 10 significant features with high information gain.

show abstract

Combining Multiple Artificial Neural Networks Using Random Committee to Decide upon Electrical Disturbance Classification

Cited by 19 publications

References 10 publications

A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation

A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation

Histogram-Based Descriptor Subset Selection for Visual Recognition of Industrial Parts

Automatic Detection of Sleep Stages based on Accelerometer Signals from a Wristband

Contact Info

Product

Resources

About