The focus of the present research endeavour is to propose a single channel Electromyogram (EMG) signal driven continuous terrain identification method utilizing a simple classifier. An iterative feature selection algorithm has also been proposed to provide effective information to the classifiers. The proposed method has been validated on EMG signal of fifteen subjects and ten subjects for three and five daily life terrains respectively. Feature selection algorithm has significantly improved the identification accuracy (ANOVA, p-value < 0.05) as compared to principal component analysis (PCA) technique. The average identification accuracies obtained by Support Vector Machine (SVM), Linear Discriminant Analysis (LDA) and Neural Network (NN) classifiers are 96.83 ± 0.28%, 97.45 ± 0.32% and 97.61 ± 0.22% respectively. Subject wise performance (five subjects) of individually trained classifiers shows no significant degradation and difference in performance among the subjects even for the untrained data (ANOVA, p-value > 0.05). The study has been extended to dual muscle approach for terrain identification. However, the proposed algorithm has shown similar performance even with the single muscle approach (ANOVA, p-value > 0.05). The outcome of the proposed continuous terrain identifi-cation method shows a pronounced potential in efficient lower limb prosthesis control.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Ultrasound is the most widely used imaging modality for screening of breast tumors. However, due to the presence of speckle noise in an ultrasound image, the diagnostic information gets masked and the interpretation of the breast abnormalities becomes difficult for the radiologist. The texture of the tumor region and the shape/margin characteristics are considered to be important parameters for the analysis of the breast tumors. In the present work, exhaustive experimentation has been carried out for the design of CAD systems for classification of breast tumors by considering (a) original images only, (b) despeckled images only and (c) both original and despeckled images together (hybrid approach). Total 100 breast ultrasound images (40 benign and 60 malignant) have been used for the analysis. Initially, these images have been despeckled using six filters namely Lee sigma, BayesShrink, DPAD, FI, FB and HFB filters. Total 162 features (149 texture and 13 morphological features) have been computed from both original and despeckled breast ultrasound images and SVM classifier has been used extensively for the classification. The results of the study indicate that the hybrid approach of CAD system design using texture features computed from original images combined with morphological features computed from images despeckled by DPAD filter yield optimal performance for classifica-tion of benign and malignant breast tumors with a classification accuracy of 96.0%. From the promising results of the study it can be concluded that the proposed hybrid CAD system design could be used as a second opinion tool in clinical setting.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
In the present work, the performance assessment of despeckle filtering algorithms has been carried out for (α) noise reduction in breast ultrasound images and (b) segmentation of benign and malignant tumours from breast ultrasound images. The despeckle filtering algorithms are broadly classified into eight categories namely local statistics based filters, fuzzy filters, Fourier filters, multiscale filters, non-linear iterative filters, total variation filters, non-local mean filters and hybrid filters. Total 100 breast ultrasound images (40 benign and 60 malignant) are processed using 42 despeckle filtering algorithms. A despeckling filter is considered to be appropriate if it preserves edges and features/structures of the image. Edge preservation capability of a despeckling filter is measured by beta metric (β) and feature/structure preservation capability is quantified using image quality index (IQI). It is observed that out of 42 filters, six filters namely Lee Sigma, FI, FB, HFB, BayesShrink and DPAD yield more clinically acceptable images in terms of edge and feature/structure preservation. The qualitative assessment of these images has been done on the basis of grades provided by the experienced participating radiologist. The pre-processed images are then fed to a segmentation module for segmenting the benign or malignant tumours from ultrasound images. The performance assessment of segmentation algorithm has been done quantitatively using the Jaccard index. The results of both quantitative and qualitative assessment by the radiologist indicate that the DPAD despeckle filtering algorithm yields more clinically acceptable images and results in better segmentation of benign and malignant tumours from breast ultrasound images.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.