Filter Bank Selection Research Articles

Multi-Class Classification of Upper Limb Movements With Filter Bank Task-Related Component Analysis.

The classification of limb movements can provide with control commands in non-invasive brain-computer interface. Previous studies on the classification of limb movements have focused on the classification of left/right limbs; however, the classification of different types of upper limb movements has often been ignored despite that it provides more active-evoked control commands in the brain-computer interface. Nevertheless, few machine learning method can be used as the state-of-the-art method in the multi-class classification of limb movements. This work focuses on the multi-class classification of upper limb movements and proposes the multi-class filter bank task-related component analysis (mFBTRCA) method, which consists of three steps: spatial filtering, similarity measuring and filter bank selection. The spatial filter, namely the task-related component analysis, is first used to remove noise from EEG signals. The canonical correlation measures the similarity of the spatial-filtered signals and is used for feature extraction. The correlation features are extracted from multiple low-frequency filter banks. The minimum-redundancy maximum-relevance selects the essential features from all the correlation features, and finally, the support vector machine is used to classify the selected features. The proposed method compared against previously used models is evaluated using two datasets. mFBTRCA achieved a classification accuracy of 0.4193 ± 0.0780 (7 classes) and 0.4032 ± 0.0714 (5 classes), respectively, which improves on the best accuracies achieved using the compared methods (0.3590 ± 0.0645 and 0.3159 ± 0.0736, respectively). The proposed method is expected to provide more control commands in the applications of non-invasive brain-computer interfaces.

Using empirical wavelet transform and high-order fuzzy cognitive maps for time series forecasting

Many studies on time series forecasting have employed fuzzy cognitive maps (FCMs). However, it is required to develop techniques capable of effective responses and great accuracy for large-scale non-stationary time series, such as sharp-fluctuated datasets. For forecasting such data, the present study introduces an accurate, precise, and efficient combined forecasting framework with ridge regression, high-order FCM (HFCM), and empirical wavelet transform (EWT). The proposed learning method named as EWTHFCM. This model employs EWT for non-stationary time series transformation into a multivariate sequence. The HFCM then models each multivariate time series through a node. For the optimized learning part, ridge regression is employed to perform the process for the HFCM representation of large-scale time series. The main reasons to choose the ridge regression are its circle-like phenomenon which makes it a perfect fit for being combined with EWT. This fitness is due to the optimal filter bank selection behavior and adaptivity feature of EWT, eventually making the ridge regression fast, efficient, and accurate. Subsequently, HFCM models and forecasts the multivariate time series and helps find the trend pattern. Then, the multivariate time series is reconstructed by inverse EWT to predict time series at all time steps. The root mean square error (RMSE) is measured on 15 real-life standard datasets, of which 8 are utilized to compare the proposed framework to 11 state-of-art algorithms. According to the experimental results and comparison with other research papers, we recommend using EWTHFCM as a new, superior, and accurate method for many forecasting purposes and circumstances.

Improving pre-movement pattern detection with filter bank selection

Objective. Pre-movement decoding plays an important role in detecting the onsets of actions using low-frequency electroencephalography (EEG) signals before the movement of an upper limb. In this work, a binary classification method is proposed between two different states. Approach. The proposed method, referred to as filter bank standard task-related component analysis (FBTRCA), is to incorporate filter bank selection into the standard task-related component analysis (STRCA) method. In FBTRCA, the EEG signals are first divided into multiple sub-bands which start at specific fixed frequencies and end frequencies that follow in an arithmetic sequence. The STRCA method is then applied to the EEG signals in these bands to extract CCPs. The minimum redundancy maximum relevance feature selection method is used to select essential features from these correlation patterns in all sub-bands. Finally, the selected features are classified using the binary support vector machine classifier. A convolutional neural network (CNN) is an alternative approach to select canonical correlation patterns. Main Results. Three methods were evaluated using EEG signals in the time window from 2 s before the movement onset to 1 s after the movement onset. In the binary classification between a movement state and the resting state, the FBTRCA achieved an average accuracy of 0.8968 ± 0.0847 while the accuracies of STRCA and CNN were 0.8228 ± 0.1149 and 0.8828 ± 0.0917, respectively. In the binary classification between two actions, the accuracies of STRCA, CNN, and FBTRCA were 0.6611 ± 0.1432, 0.6993 ± 0.1271, 0.7178 ± 0.1274, respectively. Feature selection using filter banks, as in FBTRCA, produces comparable results to STRCA. Significance. The proposed method provides a way to select filter banks in pre-movement decoding, and thus it improves the classification performance. The improved pre-movement decoding of single upper limb movements is expected to provide people with severe motor disabilities with a more natural, non-invasive control of their external devices.

Improved Wavelet Filter Bank Selection for Effective Feature Extraction in Alzheimer Classification

Background: Alzheimer’s disease (AD) is the primary reason for health problem. Motivation: Being degenerative and progressive with brain cells that can be intervened by health professionals in case of early recognition. Feature extraction is a technique employed for reduction of dimensionality. The features are generated for a image. The extraction of features has to be done accurately without any loss of information. Methods: In this work, a Cuckoo Search (CS) based Wavelet Filter Bank Selection algorithm for classification of Alzheimer’s has been proposed. The Ada Boost classifier, Random Forest (RF), and Classification and Regression Tree (CART) were used for the identification of the affected patient with Magnetic Resonance Imaging (MRI). Results: From results it can be found that proposed CS-based technique is used in classifying AD compared to conventional techniques.

A low-complexity 3-level filter bank design for effective restoration of audibility in digital hearing aids.

A low-complexity method for sub-band decomposition of audio signals in digital hearing aids for audibility restoration applications is described in this paper. This 3-level filter bank is capable of generating an array of 4, 8, and 16 sub-filters from a single finite impulse response filter. The prototype low pass filter is accomplished using the Parks McClellan algorithm with a minimal number of 28 multipliers. Fractional interpolation technique is utilized to generate more number of sub-bands with narrow bandwidth from the prototype filter. This filter bank can be used for patients with any degree of hearing impairment to compensate his audiogram. The selection of filter bank is based on the rate of change of impairment recorded in the audiogram. Apart from reduced complexity, the developed filter bank has the advantage of requiring only minimal hardware, which makes the implementation of cost-effective hearing aids a reality.

An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information

BackgroundCommon spatial pattern (CSP) has been an effective technique for feature extraction in electroencephalography (EEG) based brain computer interfaces (BCIs). However, motor imagery EEG signal feature extraction using CSP generally depends on the selection of the frequency bands to a great extent.MethodsIn this study, we propose a mutual information based frequency band selection approach. The idea of the proposed method is to utilize the information from all the available channels for effectively selecting the most discriminative filter banks. CSP features are extracted from multiple overlapping sub-bands. An additional sub-band has been introduced that cover the wide frequency band (7–30 Hz) and two different types of features are extracted using CSP and common spatio-spectral pattern techniques, respectively. Mutual information is then computed from the extracted features of each of these bands and the top filter banks are selected for further processing. Linear discriminant analysis is applied to the features extracted from each of the filter banks. The scores are fused together, and classification is done using support vector machine.ResultsThe proposed method is evaluated using BCI Competition III dataset IVa, BCI Competition IV dataset I and BCI Competition IV dataset IIb, and it outperformed all other competing methods achieving the lowest misclassification rate and the highest kappa coefficient on all three datasets.ConclusionsIntroducing a wide sub-band and using mutual information for selecting the most discriminative sub-bands, the proposed method shows improvement in motor imagery EEG signal classification.

Discriminative Wavelet Packet Filter Bank Selection for Pattern Recognition

This paper addresses the problem of discriminative wavelet packet (WP) filter bank selection for pattern recognition. The problem is formulated as a complexity regularized optimization criterion, where the tree-indexed structure of the WP bases is explored to find conditions for reducing this criterion to a type of minimum cost tree pruning, a method well understood in regression and classification trees (CART). For estimating the conditional mutual information, adopted to compute the fidelity criterion of the minimum cost tree-pruning problem, a nonparametric approach based on product adaptive partitions is proposed, extending the Darbellay-Vajda data-dependent partition algorithm. Finally, experimental evaluation within an automatic speech recognition (ASR) task shows that proposed solutions for the WP decomposition problem are consistent with well understood empirically determined acoustic features, and the derived feature representations yield competitive performances with respect to standard feature extraction techniques.

Service-oriented grid computing system for digital rights management (GC-DRM)

Service-oriented computing and applications have recently gained significant attention since they provide new service infrastructure and development of service-oriented technology. Under such trend and ubiquitous computing requirement, grid computing is becoming popular in scientific and enterprise computing due to its flexible deployment and implementation. In this paper, we proposed a service-oriented digital rights management (DRM) platform based on grid computing (called GC-DRM) which is in the compliance of Grid Portal standards by using porlet. The platform integrates Globus Toolkit 4 and Condor 6.9.2 and uses web 2.0 to construct the web-based user interface for providing job submission, control, management, monitor for DRM services. GC-DRM can provide different categories of services which include watermark embedding and extraction, image scrambling, visible watermark embedding, image tamper-detection and recovery. In addition, GC-DRM has been applied to analyze the robustness of digital watermark by filter bank selection and the performance can be improved in the aspect of speedup, stability and processing time compared with NaradaBrokering based Computing Power Services (NB-CPS) and Web Services based Computing Power Service (WS-CPS). Therefore, GC-DRM can be concluded as a superior service-oriented computing which provides the user friendly environment with efficient DRM service performance based on grid computing architecture.

Image description using joint distribution of filter bank responses

This paper presents a unified framework for image descriptors based on quantized joint distribution of filter bank responses and evaluates the significance of filter bank and vector quantizer selection. First, a filter bank based representation of the local binary pattern (LBP) operator is introduced, which shows that LBP can also be presented as an operator producing vector quantized filter bank responses. Maximum response 8 (MR8) and Gabor filters are widely used alternatives to the derivative filters which are used to implement LBP, and the performance of these three sets is compared in the texture categorization and face recognition tasks. Despite their small spatial support, the local derivative filters are shown to outperform Gabor and MR8 filters in texture categorization with the KTH-TIPS2 images. In face recognition task with CMU PIE images, the Gabor filter-based representation achieves the best recognition rate. Furthermore, it is shown that when the filter response vectors are quantized for histogram based joint density estimation, thresholding is clearly faster than using learned codebooks and, being robust to gray-level changes, it yields better recognition rate in most cases. Third, automatic selection of filter bank is discussed and excellent face recognition performance in the face recognition task is achieved with the optimized filter bank.

Distributed computing power service coordination based on peer-to-peer grids architecture

As computational speed, storage capacity, and communication technologies steadily progress to the advanced levels, many business employments have utilized these improvements to aggregate distributed resources in various enterprise collaborating functionalities. Recently, grid computing has been identified as a critical technology by industry for enterprise computing and business-to-business computing. The concept of peer-to-peer (P2P) network is also evolving to an expanded usage in distributed networks for sharing the resources like the content files or real-time data for enterprise applications. Therefore, it is natural to include the grids and P2P to support environments that have features of both limiting case. In this paper, a new computing design – NaradaBrokering based Computing Power Services (NB-CPS) – has been applied to utilize the P2P grid to integrate the computational grids, distributed objects, P2P networks under the hybrid environment. In this study, the approach has been applied to analyze the robustness of digital watermark by filter bank selection and the performance can be improved in the aspect of speedup, stability and processing time. NB-CPS is not only suitable for executing computing works which are able to run in batches, but also be able to solve current issues in Web Services based Computing Power Service (WS-CPS) such as system resilience, fault tolerance, efficiency of job scheduling and the instability in congested network environment.

A computing coordination based fuzzy group decision-making (CC-FGDM) for web service oriented architecture

As the demands for faster data processing and enterprise computing are increasing, the traditional client/server architecture has gradually been replaced by Grid computing or the peer-to-peer (P2P) model which can share the content or resources over the network. In this paper, a new computing architecture – computing power services (CPS) – has been applied to utilize web services and business process execution language for overcoming the issues about flexibility, compatibility and workflow management. CPS is a lightweight web services based computing power-sharing architecture, and suitable for enterprise computing tasks which can be executed in the batch processes within a trusty network. However, a real-time load balance and dispatching mechanism is needed for distributed-computing architecture like CPS in order to handle computing resources efficiently and properly. Therefore, a fuzzy group decision-making based adaptive collaboration design for CPS is proposed in this paper to provide the real-time computation coordination and quality of service. In this study, the approach has been applied to analyze the robustness of digital watermark by filter bank selection and the performance can be improved in the aspect of speedup, stability and processing time. This scheme increases the overall computing performance and shows stability for the dynamic environment.

Wavelet-based compression of medical images: filter-bank selection and evaluation

Wavelet-based image coding algorithms (lossy and lossless) use a fixed perfect reconstruction filter-bank built into the algorithm for coding and decoding of images. However, no systematic study has been performed to evaluate the coding performance of wavelet filters on medical images. We evaluated the best types of filters suitable for medical images in providing low bit rate and low computational complexity. In this study a variety of wavelet filters are used to compress and decompress computed tomography (CT) brain and abdomen images. We applied two-dimensional wavelet decomposition, quantization and reconstruction using several families of filter banks to a set of CT images. Discreet Wavelet Transform (DWT), which provides efficient framework of multi-resolution frequency was used. Compression was accomplished by applying threshold values to the wavelet coefficients. The statistical indices such as mean square error (MSE), maximum absolute error (MAE) and peak signal-to-noise ratio (PSNR) were used to quantify the effect of wavelet compression of selected images. The code was written using the wavelet and image processing toolbox of the MATLAB (version 6.1). This results show that no specific wavelet filter performs uniformly better than others except for the case of Daubechies and bi-orthogonal filters which are the best among all. MAE values achieved by these filters were 5 x 10(-14) to 12 x 10(-14) for both CT brain and abdomen images at different decomposition levels. This indicated that using these filters a very small error (approximately 7 x 10(-14)) can be achieved between original and the filtered image. The PSNR values obtained were higher for the brain than the abdomen images. For both the lossy and lossless compression, the 'most appropriate' wavelet filter should be chosen adaptively depending on the statistical properties of the image being coded to achieve higher compression ratio.