Computer Aided Diagnosis tool for Alzheimer’s Disease based on Mann–Whitney–Wilcoxon U-Test

Martínez-Murcia, Francisco Jesús; Górriz, Juan Manuel; Ramı́rez, Javier; Puntonet, Carlos G.; Salas-González, D.

doi:10.1016/j.eswa.2012.02.153

Cited by 87 publications

(45 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the proposed hybrid approach only FA/PCA/DWT feature selection methods have been used. The FA (Hsia et al, 2009;Kim et al, 2008;Martinez-Murcia et al, 2012) and PCA (Verma, Jha, & Ojha, 2015;Wang, Chiang, Hsu, & Yang, 2013) methods of feature selection have been chosen because these are standard methods and the results obtained by these methods serve as the benchmark for comparison with other methods. In other applications the DWT (Etehadtavakol, Ng, Chandran, & Rabbani, 2013;Lin, Liang, Ho, Lin, & Ma, 2014) has proved to be potential candidates for feature selection.…”

Section: Feature/technical Indicator Selection Using Fa Pca and Dwtmentioning

confidence: 99%

“…The necessary condition of FA is to find minimum factors which can represent a complete information of a whole system (Wang & Kuo, 2005). FA has been used successfully for feature selection of color guard members (Hsia, Hsu, & Jen, 2009), delay analysis (Kim, Soibelman, & Grobler, 2008), stock market prediction (Anish, Majhi, & Tonde, 2014) and development of a CAD tool for diagnosis of the Alzheimer's Disease (Martinez-Murcia, Gorriz, Ramirez, Puntone, & Salas-Gonzalez, 2012). This paper proposes an improved hybrid model by combining the factor analysis for feature selection with feedback FLANN model trained with recursive least square algorithm for efficient prediction of stock prices.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid nonlinear adaptive scheme for stock market prediction using feedback FLANN and factor analysis

Anish

Majhi

2016

Journal of the Korean Statistical Society

View full text Add to dashboard Cite

Available online xxxx AMS 2000 subject classifications: primary 97RXX secondary 97R40 Keywords: Feature selection Principal component analysis (PCA) Discrete wavelet transform (DWT) Factor analysis (FA) Stock price prediction Feedback Functional link artificial neural network (FFLANN) Recursive least square (RLS) algorithm a b s t r a c tAccurate and effective stock price prediction is very important for potential investors in deciding investment strategy. Data mining techniques have been applied to stock market prediction in recent literature. Factor analysis (FA), a powerful statistical attributes reduction technique, is chosen to select the inputs of the model from the raw data. A feedback type of the functional link artificial neural network (FFLANN) with recursive least square (RLS) training is proposed as a potential prediction model. Comparative performance measures obtained through simulation experiments of Principal component analysis (PCA) and Discrete wavelet transform (DWT) based methods for two stock indices demonstrate that the proposed model is a better alternative for prediction of stock indices with respect to several performance measures. For comparison purposes multilayer artificial neural network (MLANN), radial basis function neural network (RBFNN) and support vector machine (SVM) based models are also simulated under similar conditions and it is observed that the proposed model is superior to MLANN, RBFNN and SVM based prediction models. Further, the involvement of low computational complexity and reduced training time of the model will be better suited for online prediction purpose.

show abstract

Section: Feature/technical Indicator Selection Using Fa Pca and Dwtmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid nonlinear adaptive scheme for stock market prediction using feedback FLANN and factor analysis

Anish

Majhi

2016

Journal of the Korean Statistical Society

View full text Add to dashboard Cite

show abstract

“…To build our predictive model, we make use of the Support Vector Machines paradigm. Support Vector Machine (SVM) [17] is a recent class of statistical classification and regression techniques playing an increasing role in applications to detection problems in various engineering problems, notably in statistical signal processing, pattern recognition, image analysis [9], and communication systems. SVM with linear discriminant functions define decision hypersurfaces or hyperplanes in a multidimensional feature space, that is:…”

Section: Classifiermentioning

confidence: 99%

“…A wide range of supervised learning techniques have been combined to generate Computer Aided Diagnosis (CAD) systems that allow to detect neurodegenerative diseases, such as Alzheimer's Disease [9] or Parkinson [16]. Techniques range from the use of selection of Regions of Interest (ROIs) [5], or Single Value Decomposition strategies (SVD) [14] to more complex approaches such as Empirical Mode Decomposition (EMD) combined with Principal Component Analysis (PCA) combined method in [13].…”

Section: Introductionmentioning

confidence: 99%

Texture Features Based Detection of Parkinson’s Disease on DaTSCAN Images

Martínez-Murcia

Górriz

Ramı́rez

et al. 2013

Natural and Artificial Computation in Engineering and Medical Applications

View full text Add to dashboard Cite

Abstract. In this work, a novel approach to Computer Aided Diagnosis (CAD) system for the Parkinson's Disease (PD) is proposed. This tool is intended for physicians, and is based on fully automated methods that lead to the classification of Ioflupane/FP-CIT-I-123 (DaTSCAN) SPECT images. DaTSCAN images from the Parkinson Progression Markers Initiative (PPMI) are used to have in vivo information of the dopamine transporter density. These images are normalized, reduced (using a mask), and then a GLC matrix is computed over the whole image, extracting several Haralick texture features which will be used as a feature vector in the classification task. Using the leave-one-out cross-validation technique over the whole PPMI database, the system achieves results up to a 95.9% of accuracy, and 97.3% of sensitivity, with positive likelihood ratios over 19, demonstrating our system's ability on the detection of the Parkinson's Disease by providing robust and accurate results for clinical practical use, as well as being fast and automatic.

show abstract

“…Both SPECT and PET database images containing data for both Alzheimer's disease (AD) patients and healthy. In [4] presents a CAD system for early diagnosis of AD which consists of three stages: voxel selection using Mann-Whitney-Wilcoxon U-Test, feature extraction using Factor Analysis, and Linear Support Vector Machine (SVM) classifier had been used. Two different databases are used SPECT images and PET database had been used.…”

Section: Introductionmentioning

confidence: 99%

Feature Extraction of the Alzheimer’s Disease Images Using Different Optimization Algorithms

Dessouky¹,

El-Rashidy²

2016

J Alzheimers Dis Parkinsonism

View full text Add to dashboard Cite

Alzheimer's disease (AD) is a type of dementia that causes problems with memory, thinking and behavior. The symptoms of the AD are usually developed slowly and got worse over time, till reach to severe enough stage which can't interfere with daily tasks. This paper extract the most significant features from 3D MRI AD images using different optimization algorithms. Optimization algorithms are stochastic search methods that simulate the social behavior of species or the natural biological evolution. These algorithms had been used to get near-optimum solutions for large-scale optimization problems. This paper compares the formulation and results of five recent evolutionary optimization algorithms: Particle Swarm Optimization, Bat Algorithm, Genetic Algorithm, Pattern Search, and Simulated Annealing. A brief description of each of these five algorithms had been presented. These five optimization algorithm had been applied to two proposed AD feature extraction algorithms to get near-optimum number of features that gives higher accuracy. The comparisons among the algorithms are presented in terms of number of iteration, number of features and metric parameters. The results show that the Pattern Search optimization algorithm gives higher metric parameters values with lower number of iteration and lower number of features as compared to the other optimization algorithms.

show abstract

Computer Aided Diagnosis tool for Alzheimer’s Disease based on Mann–Whitney–Wilcoxon U-Test

Cited by 87 publications

References 25 publications

Hybrid nonlinear adaptive scheme for stock market prediction using feedback FLANN and factor analysis

Hybrid nonlinear adaptive scheme for stock market prediction using feedback FLANN and factor analysis

Texture Features Based Detection of Parkinson’s Disease on DaTSCAN Images

Feature Extraction of the Alzheimer’s Disease Images Using Different Optimization Algorithms

Contact Info

Product

Resources

About