MyMedR

Displaying publications 1 - 20 of 89 in total

Abstract:

Sort:

Fulltext Surface electromyography signal processing and classification techniques

Chowdhury RH, Reaz MB, Ali MA, Bakar AA, Chellappan K, Chang TG

Sensors (Basel), 2013;13(9):12431-66.
PMID: 24048337 DOI: 10.3390/s130912431

Electromyography (EMG) signals are becoming increasingly important in many applications, including clinical/biomedical, prosthesis or rehabilitation devices, human machine interactions, and more. However, noisy EMG signals are the major hurdles to be overcome in order to achieve improved performance in the above applications. Detection, processing and classification analysis in electromyography (EMG) is very desirable because it allows a more standardized and precise evaluation of the neurophysiological, rehabitational and assistive technological findings. This paper reviews two prominent areas; first: the pre-processing method for eliminating possible artifacts via appropriate preparation at the time of recording EMG signals, and second: a brief explanation of the different methods for processing and classifying EMG signals. This study then compares the numerous methods of analyzing EMG signals, in terms of their performance. The crux of this paper is to review the most recent developments and research studies related to the issues mentioned above.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Fulltext Sudden event recognition: a survey

Suriani NS, Hussain A, Zulkifley MA

Sensors (Basel), 2013 Aug 05;13(8):9966-98.
PMID: 23921828 DOI: 10.3390/s130809966

Event recognition is one of the most active research areas in video surveillance fields. Advancement in event recognition systems mainly aims to provide convenience, safety and an efficient lifestyle for humanity. A precise, accurate and robust approach is necessary to enable event recognition systems to respond to sudden changes in various uncontrolled environments, such as the case of an emergency, physical threat and a fire or bomb alert. The performance of sudden event recognition systems depends heavily on the accuracy of low level processing, like detection, recognition, tracking and machine learning algorithms. This survey aims to detect and characterize a sudden event, which is a subset of an abnormal event in several video surveillance applications. This paper discusses the following in detail: (1) the importance of a sudden event over a general anomalous event; (2) frameworks used in sudden event recognition; (3) the requirements and comparative studies of a sudden event recognition system and (4) various decision-making approaches for sudden event recognition. The advantages and drawbacks of using 3D images from multiple cameras for real-time application are also discussed. The paper concludes with suggestions for future research directions in sudden event recognition.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Fulltext Stochastic optimized relevance feedback particle swarm optimization for content based image retrieval

Imran M, Hashim R, Noor Elaiza AK, Irtaza A

ScientificWorldJournal, 2014;2014:752090.
PMID: 25121136 DOI: 10.1155/2014/752090

One of the major challenges for the CBIR is to bridge the gap between low level features and high level semantics according to the need of the user. To overcome this gap, relevance feedback (RF) coupled with support vector machine (SVM) has been applied successfully. However, when the feedback sample is small, the performance of the SVM based RF is often poor. To improve the performance of RF, this paper has proposed a new technique, namely, PSO-SVM-RF, which combines SVM based RF with particle swarm optimization (PSO). The aims of this proposed technique are to enhance the performance of SVM based RF and also to minimize the user interaction with the system by minimizing the RF number. The PSO-SVM-RF was tested on the coral photo gallery containing 10908 images. The results obtained from the experiments showed that the proposed PSO-SVM-RF achieved 100% accuracy in 8 feedback iterations for top 10 retrievals and 80% accuracy in 6 iterations for 100 top retrievals. This implies that with PSO-SVM-RF technique high accuracy rate is achieved at a small number of iterations.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Semi-quantitative and qualitative assessment of breast ultrasound elastography in differentiating between malignant and benign lesions

Alhabshi SM, Rahmat K, Abdul Halim N, Aziz S, Radhika S, Gan GC, et al.

Ultrasound Med Biol, 2013 Apr;39(4):568-78.
PMID: 23384468 DOI: 10.1016/j.ultrasmedbio.2012.10.016

The purpose of this study was to evaluate the diagnostic value of qualitative and semi-quantitative assessment of ultrasound elastography in differentiating between benign and malignant breast lesions. This prospective study was conducted in two tertiary medical centers. Consecutive B-mode ultrasound and real-time elastographic images were obtained for 67 malignant and 101 benign breast lesions in 168 women. Four experienced radiologists analyzed B-mode ultrasound alone and B-mode ultrasound combined with elastography independently. Conventional ultrasound findings were classified according to the American College of Radiology Breast Imaging Reporting and Data System classification. The elastographic assessment was based on qualitative and semi-quantitative parameters (i.e., strain pattern, width ratio, strain ratio). The sensitivity and specificity of combined elastography and conventional ultrasound were significantly higher than that of conventional ultrasound alone. The sensitivity, specificity, positive predictive value and negative predictive value was 97%, 61.4%, 62.5% and 96.8%, respectively, for conventional ultrasound and 100%, 93%, 99% and 90%, respectively, for combined technique. The semi-quantitative assessment with strain ratio and width ratio in elastography were the most useful parameters in differentiating between benign and malignant breast lesions. Cut-off point values for width ratio of more than 1.1 and strain ratio of more than 5.6 showed a high predictive value of malignancy with specificities of 84% and 76%, respectively (p

Matched MeSH terms: Pattern Recognition, Automated/methods*
Remote protein homology detection and fold recognition using two-layer support vector machine classifiers

Muda HM, Saad P, Othman RM

Comput Biol Med, 2011 Aug;41(8):687-99.
PMID: 21704312 DOI: 10.1016/j.compbiomed.2011.06.004

Remote protein homology detection and fold recognition refer to detection of structural homology in proteins where there are small or no similarities in the sequence. To detect protein structural classes from protein primary sequence information, homology-based methods have been developed, which can be divided to three types: discriminative classifiers, generative models for protein families and pairwise sequence comparisons. Support Vector Machines (SVM) and Neural Networks (NN) are two popular discriminative methods. Recent studies have shown that SVM has fast speed during training, more accurate and efficient compared to NN. We present a comprehensive method based on two-layer classifiers. The 1st layer is used to detect up to superfamily and family in SCOP hierarchy using optimized binary SVM classification rules. It used the kernel function known as the Bio-kernel, which incorporates the biological information in the classification process. The 2nd layer uses discriminative SVM algorithm with string kernel that will detect up to protein fold level in SCOP hierarchy. The results obtained were evaluated using mean ROC and mean MRFP and the significance of the result produced with pairwise t-test was tested. Experimental results show that our approaches significantly improve the performance of remote protein homology detection and fold recognition for all three different version SCOP datasets (1.53, 1.67 and 1.73). We achieved 4.19% improvements in term of mean ROC in SCOP 1.53, 4.75% in SCOP 1.67 and 4.03% in SCOP 1.73 datasets when compared to the result produced by well-known methods. The combination of first layer and second layer of BioSVM-2L performs well in remote homology detection and fold recognition even in three different versions of datasets.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Fulltext Real-Time Human Detection for Aerial Captured Video Sequences via Deep Models

AlDahoul N, Md Sabri AQ, Mansoor AM

Comput Intell Neurosci, 2018;2018:1639561.
PMID: 29623089 DOI: 10.1155/2018/1639561

Human detection in videos plays an important role in various real life applications. Most of traditional approaches depend on utilizing handcrafted features which are problem-dependent and optimal for specific tasks. Moreover, they are highly susceptible to dynamical events such as illumination changes, camera jitter, and variations in object sizes. On the other hand, the proposed feature learning approaches are cheaper and easier because highly abstract and discriminative features can be produced automatically without the need of expert knowledge. In this paper, we utilize automatic feature learning methods which combine optical flow and three different deep models (i.e., supervised convolutional neural network (S-CNN), pretrained CNN feature extractor, and hierarchical extreme learning machine) for human detection in videos captured using a nonstatic camera on an aerial platform with varying altitudes. The models are trained and tested on the publicly available and highly challenging UCF-ARG aerial dataset. The comparison between these models in terms of training, testing accuracy, and learning speed is analyzed. The performance evaluation considers five human actions (digging, waving, throwing, walking, and running). Experimental results demonstrated that the proposed methods are successful for human detection task. Pretrained CNN produces an average accuracy of 98.09%. S-CNN produces an average accuracy of 95.6% with soft-max and 91.7% with Support Vector Machines (SVM). H-ELM has an average accuracy of 95.9%. Using a normal Central Processing Unit (CPU), H-ELM's training time takes 445 seconds. Learning in S-CNN takes 770 seconds with a high performance Graphical Processing Unit (GPU).

Matched MeSH terms: Pattern Recognition, Automated/methods*
Random walker with improved weighting function for interactive medical image segmentation

Yin LK, Rajeswari M

Biomed Mater Eng, 2014;24(6):3333-41.
PMID: 25227043 DOI: 10.3233/BME-141156

To segment an image using the random walks algorithm; users are often required to initialize the approximate locations of the objects and background in the image. Due to its segmenting model that is mainly reflected by the relationship among the neighborhood pixels and its boundary conditions, random walks algorithm has made itself sensitive to the inputs of the seeds. Instead of considering the relationship between the neighborhood pixels solely, an attempt has been made to modify the weighting function that accounts for the intensity changes between the neighborhood nodes. Local affiliation within the defined neighborhood region of the two nodes is taken into consideration by incorporating an extra penalty term into the weighting function. Besides that, to better segment images, particularly medical images with texture features, GLCM variance is incorporated into the weighting function through kernel density estimation (KDE). The probability density of each pixel belonging to the initialized seeds is estimated and integrated into the weighting function. To test the performance of the proposed weighting model, several medical images that mainly made up of 174-brain tumor images are experimented. These experiments establish that the proposed method produces better segmentation results than the original random walks.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Random multispace quantization as an analytic mechanism for BioHashing of biometric and random identity inputs

Teoh AB, Goh A, Ngo DC

IEEE Trans Pattern Anal Mach Intell, 2006 Dec;28(12):1892-901.
PMID: 17108365

Biometric analysis for identity verification is becoming a widespread reality. Such implementations necessitate large-scale capture and storage of biometric data, which raises serious issues in terms of data privacy and (if such data is compromised) identity theft. These problems stem from the essential permanence of biometric data, which (unlike secret passwords or physical tokens) cannot be refreshed or reissued if compromised. Our previously presented biometric-hash framework prescribes the integration of external (password or token-derived) randomness with user-specific biometrics, resulting in bitstring outputs with security characteristics (i.e., noninvertibility) comparable to cryptographic ciphers or hashes. The resultant BioHashes are hence cancellable, i.e., straightforwardly revoked and reissued (via refreshed password or reissued token) if compromised. BioHashing furthermore enhances recognition effectiveness, which is explained in this paper as arising from the Random Multispace Quantization (RMQ) of biometric and external random inputs.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Quantitative assessment of breast density from digitized mammograms into Tabar's patterns

Jamal N, Ng KH, Looi LM, McLean D, Zulfiqar A, Tan SP, et al.

Phys Med Biol, 2006 Nov 21;51(22):5843-57.
PMID: 17068368

We describe a semi-automated technique for the quantitative assessment of breast density from digitized mammograms in comparison with patterns suggested by Tabar. It was developed using the MATLAB-based graphical user interface applications. It is based on an interactive thresholding method, after a short automated method that shows the fibroglandular tissue area, breast area and breast density each time new thresholds are placed on the image. The breast density is taken as a percentage of the fibroglandular tissue to the breast tissue areas. It was tested in four different ways, namely by examining: (i) correlation of the quantitative assessment results with subjective classification, (ii) classification performance using the quantitative assessment technique, (iii) interobserver agreement and (iv) intraobserver agreement. The results of the quantitative assessment correlated well (r2 = 0.92) with the subjective Tabar patterns classified by the radiologist (correctly classified 83% of digitized mammograms). The average kappa coefficient for the agreement between the readers was 0.63. This indicated moderate agreement between the three observers in classifying breast density using the quantitative assessment technique. The kappa coefficient of 0.75 for intraobserver agreement reflected good agreement between two sets of readings. The technique may be useful as a supplement to the radiologist's assessment in classifying mammograms into Tabar's pattern associated with breast cancer risk.

Matched MeSH terms: Pattern Recognition, Automated/methods
Quantification of diffusion tensor imaging in normal white matter maturation of early childhood using an automated processing pipeline

Loh KB, Ramli N, Tan LK, Roziah M, Rahmat K, Ariffin H

Eur Radiol, 2012 Jul;22(7):1413-26.
PMID: 22434420 DOI: 10.1007/s00330-012-2396-3

OBJECTIVES: The degree and status of white matter myelination can be sensitively monitored using diffusion tensor imaging (DTI). This study looks at the measurement of fractional anistropy (FA) and mean diffusivity (MD) using an automated ROI with an existing DTI atlas.
METHODS: Anatomical MRI and structural DTI were performed cross-sectionally on 26 normal children (newborn to 48 months old), using 1.5-T MRI. The automated processing pipeline was implemented to convert diffusion-weighted images into the NIfTI format. DTI-TK software was used to register the processed images to the ICBM DTI-81 atlas, while AFNI software was used for automated atlas-based volumes of interest (VOIs) and statistical value extraction.
RESULTS: DTI exhibited consistent grey-white matter contrast. Triphasic temporal variation of the FA and MD values was noted, with FA increasing and MD decreasing rapidly early in the first 12 months. The second phase lasted 12-24 months during which the rate of FA and MD changes was reduced. After 24 months, the FA and MD values plateaued.
CONCLUSION: DTI is a superior technique to conventional MR imaging in depicting WM maturation. The use of the automated processing pipeline provides a reliable environment for quantitative analysis of high-throughput DTI data.
KEY POINTS: Diffusion tensor imaging outperforms conventional MRI in depicting white matter maturation. • DTI will become an important clinical tool for diagnosing paediatric neurological diseases. • DTI appears especially helpful for developmental abnormalities, tumours and white matter disease. • An automated processing pipeline assists quantitative analysis of high throughput DTI data.

Matched MeSH terms: Pattern Recognition, Automated/methods
Fulltext QuaBingo: A Prediction System for Protein Quaternary Structure Attributes Using Block Composition

Tung CH, Chen CW, Guo RC, Ng HF, Chu YW

Biomed Res Int, 2016;2016:9480276.
PMID: 27610389 DOI: 10.1155/2016/9480276

Background. Quaternary structures of proteins are closely relevant to gene regulation, signal transduction, and many other biological functions of proteins. In the current study, a new method based on protein-conserved motif composition in block format for feature extraction is proposed, which is termed block composition. Results. The protein quaternary assembly states prediction system which combines blocks with functional domain composition, called QuaBingo, is constructed by three layers of classifiers that can categorize quaternary structural attributes of monomer, homooligomer, and heterooligomer. The building of the first layer classifier uses support vector machines (SVM) based on blocks and functional domains of proteins, and the second layer SVM was utilized to process the outputs of the first layer. Finally, the result is determined by the Random Forest of the third layer. We compared the effectiveness of the combination of block composition, functional domain composition, and pseudoamino acid composition of the model. In the 11 kinds of functional protein families, QuaBingo is 23% of Matthews Correlation Coefficient (MCC) higher than the existing prediction system. The results also revealed the biological characterization of the top five block compositions. Conclusions. QuaBingo provides better predictive ability for predicting the quaternary structural attributes of proteins.

Matched MeSH terms: Pattern Recognition, Automated/methods
Profiling the features of pre-segmented healthy liver CT scans: towards fast detection of liver lesions in emergency scenario

Pasha MF, Hong KS, Rajeswari M

Annu Int Conf IEEE Eng Med Biol Soc, 2011;2011:5169-73.
PMID: 22255503 DOI: 10.1109/IEMBS.2011.6091280

Automating the detection of lesions in liver CT scans requires a high performance and robust solution. With CT-scan start to become the norm in emergency department, the need for a fast and efficient liver lesions detection method is arising. In this paper, we propose a fast and evolvable method to profile the features of pre-segmented healthy liver and use it to detect the presence of liver lesions in emergency scenario. Our preliminary experiment with the MICCAI 2007 grand challenge datasets shows promising results of a fast training time, ability to evolve the produced healthy liver profiles, and accurate detection of the liver lesions. Lastly, the future work directions are also presented.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Fulltext Primary stability recognition of the newly designed cementless femoral stem using digital signal processing

Baharuddin MY, Salleh ShH, Hamedi M, Zulkifly AH, Lee MH, Mohd Noor A, et al.

Biomed Res Int, 2014;2014:478248.
PMID: 24800230 DOI: 10.1155/2014/478248

Stress shielding and micromotion are two major issues which determine the success of newly designed cementless femoral stems. The correlation of experimental validation with finite element analysis (FEA) is commonly used to evaluate the stress distribution and fixation stability of the stem within the femoral canal. This paper focused on the applications of feature extraction and pattern recognition using support vector machine (SVM) to determine the primary stability of the implant. We measured strain with triaxial rosette at the metaphyseal region and micromotion with linear variable direct transducer proximally and distally using composite femora. The root mean squares technique is used to feed the classifier which provides maximum likelihood estimation of amplitude, and radial basis function is used as the kernel parameter which mapped the datasets into separable hyperplanes. The results showed 100% pattern recognition accuracy using SVM for both strain and micromotion. This indicates that DSP could be applied in determining the femoral stem primary stability with high pattern recognition accuracy in biomechanical testing.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Optimization of MFCC parameters using Particle Swarm Optimization for diagnosis of infant hypothyroidism using Multi- Layer Perceptron

Zabidi A, Lee YK, Mansor W, Yassin IM, Sahak R

Annu Int Conf IEEE Eng Med Biol Soc, 2010;2010:1417-20.
PMID: 21096346 DOI: 10.1109/IEMBS.2010.5626712

This paper presents a new application of the Particle Swarm Optimization (PSO) algorithm to optimize Mel Frequency Cepstrum Coefficients (MFCC) parameters, in order to extract an optimal feature set for diagnosis of hypothyroidism in infants using Multi-Layer Perceptrons (MLP) neural network. MFCC features is influenced by the number of filter banks (f(b)) and the number of coefficients (n(c)) used. These parameters are critical in representation of the features as they affect the resolution and dimensionality of the features. In this paper, the PSO algorithm was used to optimize the values of f(b) and n(c). The MFCC features based on the PSO optimization were extracted from healthy and unhealthy infant cry signals and used to train MLP in the classification of hypothyroid infant cries. The results indicate that the PSO algorithm could determine the optimum combination of f(b) and n(c) that produce the best classification accuracy of the MLP.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Objective assessment of psoriasis erythema for PASI scoring

Ahmad Fadzil MH, Ihtatho D, Affandi AM, Hussein SH

Annu Int Conf IEEE Eng Med Biol Soc, 2008;2008:4070-3.
PMID: 19163606 DOI: 10.1109/IEMBS.2008.4650103

Skin colour is vital information in dermatological diagnosis. It reflects pathological condition beneath the skin and commonly being used to indicate the extent of a disease. Psoriasis is a skin disease which is indicated by the appearance of red plaques. Although there is no cure for psoriasis, there are many treatment modalities to help control the disease. To evaluate treatment efficacy, PASI (Psoriasis Area and Severity Index) which is the current gold standard method is used to determine severity of psoriasis lesion. Erythema (redness) is one parameter in PASI. Commonly, the erythema is assessed visually, thus leading to subjective and inconsistent result. In this work, we proposed an objective assessment of psoriasis erythema for PASI scoring. The colour of psoriasis lesion is analyzed by DeltaL, Deltahue, and Deltachroma of CIELAB colour space. References of lesion with different scores are obtained from the selected lesions by two dermatologists. Results based on 38 lesions from 22 patients with various level of skin pigmentation show that PASI erythema score can be determined objectively and consistent with dermatology scoring.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Novel techniques for enhancement and segmentation of acne vulgaris lesions

Malik AS, Humayun J, Kamel N, Yap FB

Skin Res Technol, 2014 Aug;20(3):322-31.
PMID: 24329769 DOI: 10.1111/srt.12122

BACKGROUND: More than 99% acne patients suffer from acne vulgaris. While diagnosing the severity of acne vulgaris lesions, dermatologists have observed inter-rater and intra-rater variability in diagnosis results. This is because during assessment, identifying lesion types and their counting is a tedious job for dermatologists. To make the assessment job objective and easier for dermatologists, an automated system based on image processing methods is proposed in this study.
OBJECTIVES: There are two main objectives: (i) to develop an algorithm for the enhancement of various acne vulgaris lesions; and (ii) to develop a method for the segmentation of enhanced acne vulgaris lesions.
METHODS: For the first objective, an algorithm is developed based on the theory of high dynamic range (HDR) images. The proposed algorithm uses local rank transform to generate the HDR images from a single acne image followed by the log transformation. Then, segmentation is performed by clustering the pixels based on Mahalanobis distance of each pixel from spectral models of acne vulgaris lesions.
RESULTS: Two metrics are used to evaluate the enhancement of acne vulgaris lesions, i.e., contrast improvement factor (CIF) and image contrast normalization (ICN). The proposed algorithm is compared with two other methods. The proposed enhancement algorithm shows better result than both the other methods based on CIF and ICN. In addition, sensitivity and specificity are calculated for the segmentation results. The proposed segmentation method shows higher sensitivity and specificity than other methods.
CONCLUSION: This article specifically discusses the contrast enhancement and segmentation for automated diagnosis system of acne vulgaris lesions. The results are promising that can be used for further classification of acne vulgaris lesions for final grading of the lesions.
KEYWORDS: acne grading; acne lesions; acne vulgaris; enhancement; segmentation

Matched MeSH terms: Pattern Recognition, Automated/methods*
Novel direct and self-regulating approaches to determine optimum growing multi-experts network structure

Loo CK, Rajeswari M, Rao MV

IEEE Trans Neural Netw, 2004 Nov;15(6):1378-95.
PMID: 15565767

This paper presents two novel approaches to determine optimum growing multi-experts network (GMN) structure. The first method called direct method deals with expertise domain and levels in connection with local experts. The growing neural gas (GNG) algorithm is used to cluster the local experts. The concept of error distribution is used to apportion error among the local experts. After reaching the specified size of the network, redundant experts removal algorithm is invoked to prune the size of the network based on the ranking of the experts. However, GMN is not ergonomic due to too many network control parameters. Therefore, a self-regulating GMN (SGMN) algorithm is proposed. SGMN adopts self-adaptive learning rates for gradient-descent learning rules. In addition, SGMN adopts a more rigorous clustering method called fully self-organized simplified adaptive resonance theory in a modified form. Experimental results show SGMN obtains comparative or even better performance than GMN in four benchmark examples, with reduced sensitivity to learning parameters setting. Moreover, both GMN and SGMN outperform the other neural networks and statistical models. The efficacy of SGMN is further justified in three industrial applications and a control problem. It provides consistent results besides holding out a profound potential and promise for building a novel type of nonlinear model consisting of several local linear models.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Neural network classification of autoregressive features from electroencephalogram signals for brain-computer interface design

Huan NJ, Palaniappan R

J Neural Eng, 2004 Sep;1(3):142-50.
PMID: 15876633

In this paper, we have designed a two-state brain-computer interface (BCI) using neural network (NN) classification of autoregressive (AR) features from electroencephalogram (EEG) signals extracted during mental tasks. The main purpose of the study is to use Keirn and Aunon's data to investigate the performance of different mental task combinations and different AR features for BCI design for individual subjects. In the experimental study, EEG signals from five mental tasks were recorded from four subjects. Different combinations of two mental tasks were studied for each subject. Six different feature extraction methods were used to extract the features from the EEG signals: AR coefficients computed with Burg's algorithm, AR coefficients computed with a least-squares (LS) algorithm and adaptive autoregressive (AAR) coefficients computed with a least-mean-square (LMS) algorithm. All the methods used order six applied to 125 data points and these three methods were repeated with the same data but with segmentation into five segments in increments of 25 data points. The multilayer perceptron NN trained by the back-propagation algorithm (MLP-BP) and linear discriminant analysis (LDA) were used to classify the computed features into different categories that represent the mental tasks. We compared the classification performances among the six different feature extraction methods. The results showed that sixth-order AR coefficients with the LS algorithm without segmentation gave the best performance (93.10%) using MLP-BP and (97.00%) using LDA. The results also showed that the segmentation and AAR methods are not suitable for this set of EEG signals. We conclude that, for different subjects, the best mental task combinations are different and proper selection of mental tasks and feature extraction methods are essential for the BCI design.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Fulltext Naive Bayes-guided bat algorithm for feature selection

Taha AM, Mustapha A, Chen SD

ScientificWorldJournal, 2013;2013:325973.
PMID: 24396295 DOI: 10.1155/2013/325973

When the amount of data and information is said to double in every 20 months or so, feature selection has become highly important and beneficial. Further improvements in feature selection will positively affect a wide array of applications in fields such as pattern recognition, machine learning, or signal processing. Bio-inspired method called Bat Algorithm hybridized with a Naive Bayes classifier has been presented in this work. The performance of the proposed feature selection algorithm was investigated using twelve benchmark datasets from different domains and was compared to three other well-known feature selection algorithms. Discussion focused on four perspectives: number of features, classification accuracy, stability, and feature generalization. The results showed that BANB significantly outperformed other algorithms in selecting lower number of features, hence removing irrelevant, redundant, or noisy features while maintaining the classification accuracy. BANB is also proven to be more stable than other methods and is capable of producing more general feature subsets.

Matched MeSH terms: Pattern Recognition, Automated/methods*
Fulltext Multistrategy self-organizing map learning for classification problems

Hasan S, Shamsuddin SM

Comput Intell Neurosci, 2011;2011:121787.
PMID: 21876686 DOI: 10.1155/2011/121787

Multistrategy Learning of Self-Organizing Map (SOM) and Particle Swarm Optimization (PSO) is commonly implemented in clustering domain due to its capabilities in handling complex data characteristics. However, some of these multistrategy learning architectures have weaknesses such as slow convergence time always being trapped in the local minima. This paper proposes multistrategy learning of SOM lattice structure with Particle Swarm Optimisation which is called ESOMPSO for solving various classification problems. The enhancement of SOM lattice structure is implemented by introducing a new hexagon formulation for better mapping quality in data classification and labeling. The weights of the enhanced SOM are optimised using PSO to obtain better output quality. The proposed method has been tested on various standard datasets with substantial comparisons with existing SOM network and various distance measurement. The results show that our proposed method yields a promising result with better average accuracy and quantisation errors compared to the other methods as well as convincing significant test.

Matched MeSH terms: Pattern Recognition, Automated/methods

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links