BackgroundThe compressed sensing (CS) of acceleration data has been drawing increasing attention in gait telemonitoring application. In such application, there still exist some challenging issues including high energy consumption of body-worn device for acceleration data acquisition and the poor reconstruction performance due to nonsparsity of acceleration data. Thus, the novel scheme of compressive sensing of acceleration data is needed urgently for solutions that are found to these issues.MethodsIn our scheme, the sparse binary matrix is firstly designed as an optimal measurement matrix only containing a smallest number of nonzero entries. And then the block sparse Bayesian learning (BSBL) algorithm is introduced to reconstruct acceleration data with high fidelity by exploiting block sparsity. Finally, some commonly used gait classification models such as multilayer perceptron (MLP), support vector machine (SVM) and KStar are applied to further validate the feasibility of our scheme for gait telemonitoring application.ResultsThe acceleration data were selected from open Human Activity Dataset of Southern California University (USC-HAD). The optimal sparse binary matrix (a smallest number of nonzero entries is 8) is as strong as the full optimal measurement matrix such as Gaussian random matrix. Moreover, BSBL algorithm significantly outperforms existing conventional CS reconstruction algorithms, and reaches the maximal signal-to-noise ratio value (70 dB). In comparison, MLP is best for gait classification, and it can classify upstairs and downstairs patterns with best accuracy of 95 % and seven gait patterns with maximal accuracy of 92 %, respectively.ConclusionsThese results show that sparse binary matrix and BSBL algorithm are feasibly applied in compressive sensing of acceleration data to achieve the perfect compression and reconstruction performance, which has a great potential for gait telemonitoring application.

The carpet industry is no longer a small business done in the villages on a small scale; instead, it has carved an altogether different space, identity, and appreciation for itself in the cosmopolitan world. As computers are is becoming more and more ubiquitous, most industries, including the carpet industry, use computers for quality improvement, accuracy enhancement, speed development, and cost reduction purposes. Unlike traditional carpet maps, many modern maps include images of human faces for hand‐woven carpet tableau. These digital images comprise millions of colors and thousands of pixels, making it practically impossible to construct and weave the carpet in the same dimensions. Many weavers currently use manual and experience‐based methods for reducing the size and number of hues for making a hand‐woven carpet tableau map. Therefore, the outcomes are not the optimal results and can be improved. Also, many color reduction methods do not focus on the hand‐woven carpet tableau map. To overcome these problems and gaps, this research focuses on proposing a new automatic method for reducing the size of color images without compromising facial nuances, lessening the number of colors used while protecting the important areas of the images, and transforming those images into carpet tableau maps. The proposed approach inputs the original color image. It continuously detecting the face and specifying important areas, and finally, outputs carpet tableau map that is proportional to the given dimensions and color count. To evaluate the proposed method, MATLAB, as a powerful simulation tool, was employed. Final results are compared to the existing approaches in terms of face detection, size reduction, and color quantization. The obtained results have shown that the approach improves speed by 39% in face detection and increases the precision of size reduction and color quantization phases. The results have also confirmed that when images of human faces are reduced by a proposed method to form an appropriate image for tableau maps, they are nearly always perceived as more attractive than the reduced faces via traditional methods.

No abstract

No abstract

An unsupervised segmentation and its performance evaluation technique are proposed for synthetic aperture radar (SAR) image based on the mixture multiscale autoregressive (MMAR) model and the bootstrap method. The segmentation-evaluation techniques consist of detecting the number of image regains, estimating MMAR parameters by using bootstrap stochastic annealing expectation-maximization (BSAEM) algorithm, and classifying pixels into region by using Bayesian classifier. Experimental results demonstrate that the evaluation operation is robust, and the proposed segmentation method is superior to the traditional single resolution techniques, and considerably reduces the computing time over the EM algorithm. OCIS codes: 100.0100, 280.6730.