Search results

As the limited energy of wireless sensor networks (WSNs), energy-efficient data-gathering algorithms are required. This paper proposes a compressive data-gathering algorithm based on double sparse structure dictionary learning (DSSDL). The purpose of this paper is to reduce the energy consumption of WSNs.

The historical data is used to construct a sparse representation base. In the dictionary-learning stage, the sparse representation matrix is decomposed into the product of double sparse matrices. Then, in the update stage of the dictionary, the sparse representation matrix is orthogonalized and unitized. The finally obtained double sparse structure dictionary is applied to the compressive data gathering in WSNs.

The dictionary obtained by the proposed algorithm has better sparse representation ability. The experimental results show that, the sparse representation error can be reduced by at least 3.6% compared with other dictionaries. In addition, the better sparse representation ability makes the WSNs achieve less measurement times under the same accuracy of data gathering, which means more energy saving. According to the results of simulation, the proposed algorithm can reduce the energy consumption by at least 2.7% compared with other compressive data-gathering methods under the same data-gathering accuracy.

In this paper, the double sparse structure dictionary is introduced into the compressive data-gathering algorithm in WSNs. The experimental results indicate that the proposed algorithm has good performance on energy consumption and sparse representation.

To find a successful human action recognition system (HAR) for the unmanned environments.

This paper describes the key technology of an efficient HAR system. In this paper, the advancements for three key steps of the HAR system are presented to improve the accuracy of the existing HAR systems. The key steps are feature extraction, feature descriptor and action classification, which are implemented and analyzed. The usage of the implemented HAR system in the self-driving car is summarized. Finally, the results of the HAR system and other existing action recognition systems are compared.

This paper exhibits the proposed modification and improvements in the HAR system, namely the skeleton-based spatiotemporal interest points (STIP) feature and the improved discriminative sparse descriptor for the identified feature and the linear action classification.

The experiments are carried out on captured benchmark data sets and need to be analyzed in a real-time environment.

The middleware support between the proposed HAR system and the self-driven car system provides several other challenging opportunities in research.

The authors’ work provides the way to go a step ahead in machine vision especially in self-driving cars.

The method for extracting the new feature and constructing an improved discriminative sparse feature descriptor has been introduced.

Electrical impedance tomography (EIT) is a technique for reconstructing the conductivity distribution by injecting currents at the boundary of a subject and measuring the resulting changes in voltage. Image reconstruction for EIT is a nonlinear problem. A generalized inverse operator is usually ill-posed and ill-conditioned. Therefore, the solutions for EIT are not unique and highly sensitive to the measurement noise.

This paper develops a novel image reconstruction algorithm for EIT based on patch-based sparse representation. The sparsifying dictionary optimization and image reconstruction are performed alternately. Two patch-based sparsity, namely, square-patch sparsity and column-patch sparsity, are discussed and compared with the global sparsity.

Both simulation and experimental results indicate that the patch based sparsity method can improve the quality of image reconstruction and tolerate a relatively high level of noise in the measured voltages.

EIT image is reconstructed based on patch-based sparse representation. Square-patch sparsity and column-patch sparsity are proposed and compared. Sparse dictionary optimization and image reconstruction are performed alternately. The new method tolerates a relatively high level of noise in measured voltages.

The purpose of this paper is to find an efficient fabric defect detection algorithm by means of exploring the sparsity characteristics of main local binary pattern (MLBP) extracted from the original fabric texture.

In the proposed algorithm, original LBP features are extracted from the fabric texture to be detected, and MLBP are selected by occurrence probability. Second, a dictionary is established with MLBP atoms which can sparsely represent all the LBP. Then, the value of the gray-scale difference between gray level of neighborhood pixels and the central pixel, and the mean of the difference which has the same MLBP feature are calculated. And then, the defect-contained image is reconstructed as normal texture image. Finally, the residual is calculated between reconstructed and original images, and a simple threshold segmentation method can divide the residual image, and the defective region is detected.

The experiment result shows that the fabric texture can be more efficiently reconstructed, and the proposed method achieves better defect detection performance. Moreover, it offers empirical insights about how to exploit the sparsity of one certain feature, e.g. LBP.

Because of the selected research approach, the results may lack generalizability in chambray. Therefore, researchers are encouraged to test the proposed propositions further.

In this paper, a novel fabric defect detection method which extracts the sparsity of MLBP features is proposed.

In the past few decades, the content-based image retrieval (CBIR), which focuses on the exploration of image feature extraction methods, has been widely investigated. The term of feature extraction is used in two cases: application-based feature expression and mathematical approaches for dimensionality reduction. Feature expression is a technique of describing the image color, texture and shape information with feature descriptors; thus, obtaining effective image features expression is the key to extracting high-level semantic information. However, most of the previous studies regarding image feature extraction and expression methods in the CBIR have not performed systematic research. This paper aims to introduce the basic image low-level feature expression techniques for color, texture and shape features that have been developed in recent years.

First, this review outlines the development process and expounds the principle of various image feature extraction methods, such as color, texture and shape feature expression. Second, some of the most commonly used image low-level expression algorithms are implemented, and the benefits and drawbacks are summarized. Third, the effectiveness of the global and local features in image retrieval, including some classical models and their illustrations provided by part of our experiment, are analyzed. Fourth, the sparse representation and similarity measurement methods are introduced, and the retrieval performance of statistical methods is evaluated and compared.

The core of this survey is to review the state of the image low-level expression methods and study the pros and cons of each method, their applicable occasions and certain implementation measures. This review notes that image peculiarities of single-feature descriptions may lead to unsatisfactory image retrieval capabilities, which have significant singularity and considerable limitations and challenges in the CBIR.

A comprehensive review of the latest developments in image retrieval using low-level feature expression techniques is provided in this paper. This review not only introduces the major approaches for image low-level feature expression but also supplies a pertinent reference for those engaging in research regarding image feature extraction.

Most layer‐based rapid prototyping systems use polygonal models as input. In addition, the input polygonal models need to be manifold and water‐tight; otherwise the built objects may have defects or the building process may fail in some cases. This paper aims to present a regulation method of an arbitrarily complex polygonal model for rapid prototyping and manufacturing applications.

The method is based on a semi‐implicit representation of a solid model named the layered depth‐normal images (LDNI), which sparsely encodes the shape boundary of a polygonal model in three orthogonal directions. In the method, input polygonal models or parametric equations are first converted into LDNI models. A regulation operator based on the computed LDNI models is presented. A volume tiling technique is developed for very complex geometries and high accuracy requirements. From the processed LDNI model, an adaptive contouring method is presented to construct a cell representation that includes both uniform and octree cells. Finally, two‐manifold and water‐tight polygonal mesh surfaces are constructed from the cell representation.

The LDNI‐based mesh regulation operation can be robust due to its simplicity. The accuracy of the generated regulated models can be controlled by setting LDNI pixel width. Parallel computing techniques can be employed to accelerate the computation in the LDNI‐based method. Experimental results on various CAD models demonstrate the effectiveness and efficiency of our approach for complex geometries.

The input polygonal model is assumed to be closed in our method. The regulated polygonal model based on our method may have a big file size.

A novel mesh regulation method is presented in this paper. The method is suitable for rapid prototyping and manufacturing applications by achieving a balance between simplicity, robustness, accuracy, speed and scalability. This research contributes to the additive manufacturing development by providing a digital data preparation method and related tools.

This paper aims to provide a framework of the supervised hyperspectral classification, to study the traditional flowchart of hyperspectral image (HIS) analysis and processing. HSI technology has been proposed for many years, and the applications of this technology were promoted by technical advancements.

First, the properties and current situation of hyperspectral technology are summarized. Then, this paper introduces a series of common classification approaches. In addition, a comparison of different classification approaches on real hyperspectral data is conducted. Finally, this survey presents a discussion on the classification results and points out the classification development tendency.

The core of this survey is to review of the state of the art of the classification for hyperspectral images, to study the performance and efficiency of certain implementation measures and to point out the challenges still exist.

The study categorized the supervised classification for hyperspectral images, demonstrated the comparisons among these methods and pointed out the challenges that still exist.

The use of artificial intelligence (AI) in management research is still nascent and has primarily focused on content analyses of text data. Some method scholars have begun to discuss the potential benefits of far broader applications; however, these discussions have not led yet to a wave of corresponding AI applications by management researchers. This chapter explores the feasibility and the potential value of using AI for a very specific methodological task: the reliable and efficient capturing of higher-level psychological constructs in management research. It introduces the capturing of basic emotions and emotional authenticity of entrepreneurs based on their macro- and microfacial expressions during pitch presentations as an illustrative example of related AI opportunities and challenges. Thus, this chapter provides both motivation and guidance to management scholars for future applications of AI to advance management research.

The purpose of this paper is to explore gas/liquid two-phase flow is widely existed in industrial fields, especially in chemical engineering. Electrical resistance tomography (ERT) is considered to be one of the most promising techniques to monitor the transient flow process because of its advantages such as fast respond speed and cross-section imaging. However, maintaining high resolution in space together with low cost is still challenging for two-phase flow imaging because of the ill-conditioning of ERT inverse problem.

In this paper, a sparse reconstruction (SR) method based on the learned dictionary has been proposed for ERT, to accurately monitor the transient flow process of gas/liquid two-phase flow in a pipeline. The high-level representation of the conductivity distributions for typical flow regimes can be extracted based on denoising the deep extreme learning machine (DDELM) model, which is used as prior information for dictionary learning.

The results from simulation and dynamic experiments indicate that the proposed algorithm efficiently improves the quality of reconstructed images as compared to some typical algorithms such as Landweber and SR-discrete fourier transformation/discrete cosine transformation. Furthermore, the SR-DDELM has also used to estimate the important parameters of the chemical process, a case in point is the volume flow rate. Therefore, the SR-DDELM is considered an ideal candidate for online monitor the gas/liquid two-phase flow.

This paper fulfills a novel approach to effectively monitor the gas/liquid two-phase flow in pipelines. One deep learning model and one adaptive dictionary are trained via the same prior conductivity, respectively. The model is used to extract high-level representation. The dictionary is used to represent the features of the flow process. SR and extraction of high-level representation are performed iteratively. The new method can obviously improve the monitoring accuracy and save calculation time.

Proposes a non‐negative matrix factorization method.

Presents an algorithm for finding a suboptimal basis matrix. This is controlled by data cluster centers which can guarantee that the coefficient is very sparse. This leads to the proposition of an application of non‐matrix factorization for blind sparse source separation with less sensors than sources.

Two simulation examples reveal the validity and performance of the algorithm in this paper.

Using the approach in this paper, the sparse sources can be recovered even if the sources are overlapped to some degree.