Search

The article aims to introduce a gold-standard Pashto dataset and a segmentation app. The Pashto dataset consists of 300 line images and corresponding Pashto text from three selected books. A line image is simply an image consisting of one text line from a scanned page. To our knowledge, this is one of the first open access datasets which directly maps line images to their corresponding text in the Pashto language. We also introduce the development of a segmentation app using textbox expanding algorithms, a different approach to OCR segmentation. The authors discuss the steps to build a Pashto dataset and develop our unique approach to segmentation. The article starts with the nature of the Pashto alphabet and its unique diacritics which require special considerations for segmentation. Needs for datasets and a few available Pashto datasets are reviewed. Criteria of selection of data sources are discussed and three books were selected by our language specialist from the Afghan Digital Repository. The authors review previous segmentation methods and introduce a new approach to segmentation for Pashto content. The segmentation app and results are discussed to show readers how to adjust variables for different books. Our unique segmentation approach uses an expanding textbox method which performs very well given the nature of the Pashto scripts. The app can also be used for Persian and other languages using the Arabic writing system. The dataset can be used for OCR training, OCR testing, and machine learning applications related to content in Pashto. [ABSTRACT FROM AUTHOR]

In this paper, a Hough transformation-based method is proposed for detecting high-speed, accelerating targets and estimating their parameters. The transformation relationship between the echo walk parameter of such a target and Hough transformation (HT) polar coordinates is analyzed and, in light of HT characteristics, a partition-based HT (PHT) method is proposed. The method makes use of the principle of superposition and has the effect of increasing HT computation speed, able to meet the requirement on real time. A partition process is proposed to deal with the non-linearity of a high-acceleration target trajectory. To begin with, the acceleration of the target is estimated, then target detection and parameter estimation are carried out with compensation made for acceleration, and when it comes to weak target signals, especially for low signal-to-noise ratio (SNR) signals, the detection capability can be enhanced by free combination of partitioned submatrices. Finally, the algorithm is verified experimentally and its effectiveness is confirmed. [ABSTRACT FROM AUTHOR]

This paper proposes a time-frequency algorithm based on short-time fractional order Fourier transformation (STFRFT) for identification of a complicated movement targets. This algorithm, consisting of a STFRFT order-changing and quick selection method, is effective in reducing the computation load. A multi-order STFRFT time-frequency algorithm is also developed that makes use of the time-frequency feature of each micro-Doppler component signal. This algorithm improves the estimation accuracy of time-frequency curve fitting through multi-order matching. Finally, experiment data were used to demonstrate STFRFT's performance in micro-Doppler time-frequency analysis. The results validated the higher estimate accuracy of the proposed algorithm. It may be applied to an LFM (Linear frequency modulated) pulse radar, SAR (Synthetic aperture radar), or ISAR (Inverse synthetic aperture radar), for improving the probability of target recognition. [ABSTRACT FROM AUTHOR]

The speed of modern vehicles becomes higher and higher along with the development in supersonic technology and this brings challenge to detection by conventional radars. This article studies the problems encountered in high-speed target detection by conventional radars. Firstly, it analyzes the factors affecting the range migration of high-speed target echo envelope and gives three algorithm structures for high-speed target range migration. Secondly, this article reviews the characteristics of the three algorithm structures and, based on coordinate transformation, proposes a high-speed target detection algorithm using frequency compensation structure; this algorithm is capable of accomplishing first-order and second-order term compensation of high-speed target range migration. Finally, the validity and advantage of this algorithm are verified by experiment data. [ABSTRACT FROM AUTHOR]

Image reconstruction technology based on electrical resistance tomography (ERT) is one of the most critical voidage measurement techniques in two-phase flow because of the technology's merits, such as visualization, non-intrusiveness, and minimal effect on the environment. However, the reconstruction accuracy of ERT usually presents an enormous challenge because of its ill-posed problems in complexity. A new reconstructed algorithm based on forgetting factor-H∞ filter (FF-H∞ filter) for voidage measurement was developed in this study. The H∞ filter was applied to calculate the filter gain and error matrices for state variable formulation. The forgetting factor was then adaptively adjusted by the residual error of two adjacent times to increase the weight of real-time data and update the status variables with the gain matrix. To reduce the noise information and imaging artifacts, the fuzzy threshold de-noising method was implemented in the data processing. Simulated and practical experiments were combined to contribute to the image reconstruction study. The experiments show that compared with the traditional H∞ filter, the FF-H∞ filter can make better use of the three evaluation indexes, improve the reconstructed quality, and significantly reduce boundary artifacts. This method can obtain highly accurate voidage for online measurement because of its strong real-time data availability and antijamming capacity. [ABSTRACT FROM AUTHOR]

This paper established the fault diagnosis system of aluminum electrolysis, according to the characteristics of the faults in aluminum electrolysis. This system includes two subsystems; one is process fault subsystem and the other is fault subsystem. Process fault subsystem includes the subneural network layer and decision fusion layer. Decision fusion neural network verifies the diagnosis result of the subneural network by the information transferring over the network and gives the decision of fault synthetically. EMD algorithm is used for data preprocessing of current signal in stator of the fault subsystem. Wavelet decomposition is used to extract feature on current signal in the stator; then, the system inputs the feature to the rough neural network for fault diagnosis and fault classification. The rough neural network gives the results of fault diagnosis. The simulation results verify the feasibility of the method. [ABSTRACT FROM AUTHOR]

This work was aimed to explore the application of the L2-block-matching and 3-dimentional filtering (BM3D) (L2-BM3D) denoising algorithm in the treatment of lumbar degeneration with long- and short-segment fixation of posterior decompression. 120 patients with degenerative lumbar scoliosis were randomly divided into group A (MRI images were not processed), group B (MRI images were processed by the BM3D denoising algorithm), and group C (MRI images were processed by the BM3D denoising algorithm based on weighted norm L2). This denoising algorithm was comprehensively evaluated in terms of mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and running time. Besides, the results of surgeries based on different denoising methods were assessed through the surgical time, intraoperative blood loss, postoperative drainage, and postoperative follow-up. The results showed the following: (1) PSNR (peak signal-to-noise ratio) and SSIM (structural similarity index measure) of the L2-BM3D algorithm are better than those of the BM3D algorithm (31.21 dB versus 29.33 dB, 0.83 versus 0.72), while mean square error (MSE) was less than that of the BM3D algorithm (P < 0.05). (2) The operation time, intraoperative bleeding, and postoperative drainage volume in group C were lower than those in group B and group A (P < 0.05). The postoperative follow-up results showed that, in group C, the postoperative VAS (visual analysis scale) score (1.03 ± 0.29) and ODI (Oswestry disability index) (9.29 ± 0.32) were lower, indicating that the postoperative recovery effect of patients was better. Therefore, the patient's postoperative recovery effect was better. In conclusion, the L2-BM3D algorithm had an ideal denoising effect on MRI images of lumbar degeneration and was worthy of clinical promotion. [ABSTRACT FROM AUTHOR]

A gantry-based tri-modality system that combines bioluminescence (BLT), diffuse optical (DOT), and x-ray computed tomography (XCT) into the same setting is presented here. The purpose of this system is to perform bioluminescence tomography using a multi-modality imaging approach. As parts of this hybrid system, XCT and DOT provide anatomical information and background optical property maps. This structural and functional a priori information is used to guide and restrain bioluminescence reconstruction algorithm and ultimately improve the BLT results. The performance of the combined system is evaluated using multi-modality phantoms. In particular, a cylindrical heterogeneous multi-modality phantom that contains regions with higher optical absorption and x-ray attenuation is constructed. We showed that a 1.5 mm diameter bioluminescence inclusion can be localized accurately with the functional a priori information while its source strength can be recovered more accurately using both structural and the functional a priori information. [ABSTRACT FROM AUTHOR]

This study aimed to identify the effect of CYP2C9-VKORC1 interaction on warfarin dosage requirement and its predictive algorithm by investigating four populations. Generalized linear model was used to evaluate the relationship between the interaction and warfarin stable dosage (WSD), whereas multiple linear regression analysis was applied to construct the WSD predictive algorithm. To evaluate the effect of CYP2C9-VKORC1 interaction on the predictive algorithms, we compared the algorithms with and without the interaction. The interaction was significantly associated with WSD in the Chinese and White cohorts (P values<0.05). In the algorithms that considered the interaction, the predictive success rates improved by only 0.12% in the Chinese patients and by a maximum of 0.02% in the White patients under four different CYP2C9 classifications. Thus, VKORC1-CYP2C9 interaction can affect WSD. However, the discrepancy between the predictive results obtained using the predictive algorithm with and without CYP2C9-VKORC1 interaction was negligible and can therefore be disregarded. [ABSTRACT FROM AUTHOR]

We propose two variable weighted iterative reconstruction algorithms (VW-ART and VW-OS-SART) to improve the algebraic reconstruction technique (ART) and simultaneous algebraic reconstruction technique (SART) and establish their convergence. In the two algorithms, the weighting varies with the geometrical direction of the ray. Experimental results with both numerical simulation and real CT data demonstrate that the VW-ART has a significant improvement in the quality of reconstructed images over ART and OS-SART. Moreover, both VW-ART and VW-OS-SART are more promising in convergence speed than the ART and SART, respectively. [ABSTRACT FROM AUTHOR]

Non-linearities commonly exist in an electro-hydraulic servo shaking table, causing acceleration harmonics distortion when the shaking table is excited by a sinusoidal acceleration signal, because its acceleration response includes higher harmonics, which lower the control performance for an electro-hydraulic servo shaking table. To cancel the harmonics in the system response, thus to improve the shaking table performance, we need to know about the harmonics information. An identification algorithm is developed here based on a Kalman filter for dynamically tracking the acceleration harmonics for the electro-hydraulic servo shaking table. A linear system in state space is modelled. The system acceleration response is applied as an observation value and is imported to the Kalman filter, which recursively estimates the state vector of the linear system. The amplitude and phase of each harmonic are calculated from the estimated state vector, and their estimated values are validated. A simulation example is presented and experiments were performed on the electro-hydraulic servo shaking table. Both results show a good estimation performance of the proposed acceleration harmonic identification algorithm. [ABSTRACT FROM AUTHOR]

• Merely one nearest space vector closet to the origin requires to be detected online. • Redundant and optimized switching sequences are flexibly generated to achieve the minimum number of switching transitions. • Continuous modulation and discontinuous modulation modes are easily obtained. • It is more hardware efficient, independent of the level number and suitable for various multilevel converters. This paper presents a nearest-level-equivalent space vector modulation (SVM) algorithm for three-phase multilevel converters. The proposed algorithm provides a simple approach to obtain three modulation vectors online based on basic vectors. In addition, the principle of nearest-level modulation (NLM) is applied in the proposed SVM to make its superior performance to the generalized SVM algorithms, which present: (1) Merely one modulation vertex need to be detected and three-phase duty cycles are obtained. Therefore, the unbalanced voltages of inner cell of neutral-point-clamped cascaded multilevel converter (NPC-CMC) can be addressed; (2) Redundant and optimized switching sequences are automatically generated to minimize the number of switching transition; (3) Different modulation modes can be flexibly chosen to optimize the harmonic benefit. The proposed SVM scheme is independent of level numbers and finally verified by simulation and experimental results. [ABSTRACT FROM AUTHOR]