Uniform Features Research Articles

Multi-Level Fusion in Ultrasound for Cancer Detection based on Uniform LBP Features

Collective improvement in the acceptable or desirable accuracy level of breast cancer image-related pattern recognition using various schemes remains challenging. Despite the combination of multiple schemes to achieve superior ultrasound image pattern recognition by reducing the speckle noise, an enhanced technique is not achieved. The purpose of this study is to introduce a features-based fusion scheme based on enhancement uniform-Local Binary Pattern (LBP) and filtered noise reduction. To surmount the above limitations and achieve the aim of the study, a new descriptor that enhances the LBP features based on the new threshold has been proposed. This paper proposes a multi-level fusion scheme for the auto-classification of the static ultrasound images of breast cancer, which was attained in two stages. First, several images were generated from a single image using the pre-processing method. The median and Wiener filters were utilized to lessen the speckle noise and enhance the ultrasound image texture. This strategy allowed the extraction of a powerful feature by reducing the overlap between the benign and malignant image classes. Second, the fusion mechanism allowed the production of diverse features from different filtered images. The feasibility of using the LBP-based texture feature to categorize the ultrasound images was demonstrated. The effectiveness of the proposed scheme is tested on 250 ultrasound images comprising 100 and 150 benign and malignant images, respectively. The proposed method achieved very high accuracy (98%), sensitivity (98%), and specificity (99%). As a result, the fusion process that can help achieve a powerful decision based on different features produced from different filtered images improved the results of the new descriptor of LBP features in terms of accuracy, sensitivity, and specificity.

Facial Expression Recognition With Confidence Guided Refined Horizontal Pyramid Network

Facial expression recognition has become one of the most studied applications in computer vision and human-computer interaction. Part-level features constitute one the most appealing breakthrough to offer fine-grained information and have been intensively studied consequently. The main prerequisite is accurate location of facial parts with additional cues, which is turned to be another difficulty. Rather than directly locating parts, this paper proposes a confidence guided Refined Horizontal Pyramid Network (RHPN) to fully exploit various partial information of a given facial image. It can learn discriminative features with multiple facial granularities. Inconsistencies within each granularity are efficiently limited. Specifically, we first design a Horizontal Pyramid Network (HPN) for classification using the uniform partial feature representations at different horizontal pyramid scales. It successfully enhances the discriminative capabilities of various facial parts. Then, a refinement mechanism is added to HPN due to the fact that the uniform partition inevitably incurs outliers in each part and introduces unreasonable similarity between different parts. It re-assigns these outliers to the parts they are closest to, resulting in the refined parts with enhanced within-stripe consistency. Due to the lack of explicit supervisory information, we design an induced training strategy additionally for efficiently training of RHPN. For avoiding the finagle of prediction based on the separate feature vector, we prefer the confidence guided prediction as the final classification result. Experiments verify the effectiveness of our network for increasing the performance on facial expression recognition. More importantly, it surpasses the state-of-the-art by a large margin on the lab-controlled Oulu-CASIA dataset and the real world RAF-DB dataset.

A Multi-View Fusion Method via Tensor Learning and Gradient Descent for Image Features

In many computer vision applications, one image can be represented by multiple heterogeneous features from different views, most of them commonly locate in high-dimensional space. These features can reflect different characteristics of one same object, they contain compatible and complementary information among each other. How to construct an uniform low-dimensional embedding features which represent useful information of multi-view features is still an important and urgent issue to be solved. Therefore, we propose a multi-view fusion method via tensor learning and gradient descent (MvF-TG) in this paper. MvF-TG reconstructs a lowdimensional mapping subspace of each object by utilizing its k nearest neighbors, which preserves the underlying neighborhood structure of the original local manifold. The new method can effectively exploit the spatial correlation information from the multi-view features by tensor learning. Furthermore, the method constructs a gradient descent optimization model to generate the better unified low dimensional embedding. The proposed method is compared with several single-view and multi-view dimensional reduction methods in these indicators of P, R, MAP and F-measure. In the retrieval experiments, the P values of the newmethod respectively are 86.80%, 52.00%, 68.56% and 78.80% on datasets of Corel1k, Corel5k, Corel10k and Holidays. In the classification experiments, the mean accuracies of it respectively are 47.94% and 87.58% on datasets of Caltech101 and Coil. These values are higher than those obtained by other comparison methods, various evaluations based on the applications of image classification and retrieval demonstrates the effectiveness of our proposed method on multi-view feature fusion dimension reduction.

Relation Graph Network for 3D Object Detection in Point Clouds.

Convolutional Neural Networks (CNNs) have emerged as a powerful tool for object detection in 2D images. However, their power has not been fully realised for detecting 3D objects directly in point clouds without conversion to regular grids. Moreover, existing state-of-the-art 3D object detection methods aim to recognize objects individually without exploiting their relationships during learning or inference. In this article, we first propose a strategy that associates the predictions of direction vectors with pseudo geometric centers, leading to a win-win solution for 3D bounding box candidates regression. Secondly, we propose point attention pooling to extract uniform appearance features for each 3D object proposal, benefiting from the learned direction features, semantic features and spatial coordinates of the object points. Finally, the appearance features are used together with the position features to build 3D object-object relationship graphs for all proposals to model their co-existence. We explore the effect of relation graphs on proposals' appearance feature enhancement under supervised and unsupervised settings. The proposed relation graph network comprises a 3D object proposal generation module and a 3D relation module, making it an end-to-end trainable network for detecting 3D objects in point clouds. Experiments on challenging benchmark point cloud datasets (SunRGB-D, ScanNet and KITTI) show that our algorithm performs better than existing state-of-the-art.

Mitochondria interaction networks show altered topological patterns in Parkinson\u2019s disease

Mitochondrial dysfunction is linked to pathogenesis of Parkinson’s disease (PD). However, individual mitochondria-based analyses do not show a uniform feature in PD patients. Since mitochondria interact with each other, we hypothesize that PD-related features might exist in topological patterns of mitochondria interaction networks (MINs). Here we show that MINs formed nonclassical scale-free supernetworks in colonic ganglia both from healthy controls and PD patients; however, altered network topological patterns were observed in PD patients. These patterns were highly correlated with PD clinical scores and a machine-learning approach based on the MIN features alone accurately distinguished between patients and controls with an area-under-curve value of 0.989. The MINs of midbrain dopaminergic neurons (mDANs) derived from several genetic PD patients also displayed specific changes. CRISPR/CAS9-based genome correction of alpha-synuclein point mutations reversed the changes in MINs of mDANs. Our organelle-interaction network analysis opens another critical dimension for a deeper characterization of various complex diseases with mitochondrial dysregulation.

Mechanical characterization of FDM filaments with PVDF matrix reinforced with Graphene and Barium Titanate

In past one decade number of studies has been reported on optimization of process parameters of fused deposition modelling (FDM) for in-house developed thermoplastic composite based feed stock filaments. This paper investigates smart polymer-based composites prepared with hybrid feed stock filament (comprising of polyvinylidene fluoride (PVDF) reinforced with graphene (Gr) and barium titanate (BTO) powder). This work started with the Functional prototypes were 3D printed for tensile and flexural characterization using inhouse developed filament (PVDF (78%)+Gr (2%) with BTO (20%)) at optimized settings of FDM. The printed specimens were subjected to destructive testing for mechanical properties (to analyze the process capability indices, Cp and Cpk). For morphological properties, scanning electron microscopy (SEM) images and 3D rendered images of the fractured surfaces of tensile and flexural specimen were used. It has been revealed from the SEM and 3D rendered images that the optimized settings of 3D printing process parameters resulted into uniform morphological features (based upon surface roughness (Ra) and amplitude distribution function (ADF), peak count (PC) and bearing ratio (BR) curve).

Memristive Behaviour of Ag-doped-HfO2 Thin Films Prepared by Magnetron Sputtering

The bipolar resistive switching is suitable for the applications of information storage, logical operation and neuromorphic computation. This paper reports the bipolar resistive switching behaviour in HfO2:Ag-based memristive device. Under DC sweeps, the Ag/HfO2:Ag/p++-Si device showed a uniform bipolar resistive switching feature with a resistance ratio of ~15. Moreover, in the low voltage sweeping region, the device showed analog resistive switching behaviour with gradual SET and gradual RESET characteristics. It is suggested that the formation/rupture of Ag-filament is crucial in the resistive switching, and the gradual changes in resistance might have resulted from the dissolution of Ag atoms from active Ag top electrode (TE) rather than only from local migration of Ag atoms inside the dielectric layer. This new memristor structure with the analog resistive switching is expected for the future application of memristor as a nonvolatile memory and neuromorphic computing.

Evaluation on the pore and water-permeability of woven conical tubular vascular graft with continuous variable cross sections

Considering the wall smoothness and mechanical continuity of conical tubular vascular grafts, the conical tubular vascular graft with continuous variable cross-sections (CVC) has been successfully woven on the basis of the equal-cover-factor principle. However, the tubular wall property and its effect on water permeability is still unknown, which is one of the fundamental properties for woven vascular grafts. In this study, a series of CVC conical tubular prototypes with different conical degrees and typical fabric weaves were prepared, and their wall features and the water permeability along the tubular walls were measured. And then, the study investigated the uniformity of the wall structure as well as the relationship among water permeability, and porosity and pore sizes. The results show that these samples have statistically uniform pore features and water permeability along the graft wall, but both the pore features and the permeability are sensitive to the conical degree as well as fabric weaves. Moreover, the water permeability has a significant parabolic relationship with the pore size, while there is no significant dependence on the porosity. These results demonstrate advantages of the CVC tubular vascular graft produced in the equal-cover-factor principle, and will facilitate the development of the CVC woven tubular vascular graft.

Microstructural and mechanical aspects of micrometric and nanometric Ni + 10% Cr7C3 composite microwave clads

In this paper, we present the development of micrometric and nanometric Ni + 10% Cr7C3 composite clad on ASTM A743 grade CA6NM hydroturbine steel through microwave irradiation. The microstructure of micrometric clad exhibited blade and rod-like structure of carbides embedded in [Formula: see text](Ni, Fe) solid solution, while nanometric clad leads to the evolution of petal-like structure of carbides. The developed nanometric clad shows uniform microstructural features with a low level of carbide decomposition. As a result, the average nanohardness and fracture toughness of nanometric clad improved by 38.11% and 8%, respectively, compared to the micrometric clad. Clads have porosity of the order of 1.1% and 0.81% for micrometric and nanometric clad, respectively.

3D printed tensile and flexural prototypes of thermoplastic matrix reinforced with multi-materials: A statistical analysis

Fused deposition modelling (FDM) is one of the established low cost 3D printing techniques for preparation of functional/ non functional prototypes from thermoplastic composite matrix (prepared as multi/ hybrid blended material). But hitherto little has been reported on multi material reinforced thermoplastic matrix in successive 3D printed layers from repeatability view point. Since the adaptability of any processing technique is dependent upon repeatability/ reproducibility (for which the process output must be statistically controlled), this work reports the statistical analysis of 3D printed tensile and flexural samples printed on FDM as functional prototypes of poly lactic acid (PLA) matrix reinforced with multi materials (poly vinyl chloride (PVC), wood dust and magnetite (Fe 3 O 4 ) powder) as functionally graded thermoplastic matrix. Further in this work functional prototypes of tensile and flexural sample were 3D printed and tested for their mechanical properties to analyze the process capability index (Cp and Cpk) along with morphological characteristics using optical images of the fractured surfaces. The result of the study suggests that the process was observed to be in statistical control as Cp and Cpk was found to be more than 1 for tensile and flexural properties. Based upon optical photo micrographs it has been ascertained that the optimized 3D printing parameters resulted into uniform morphological features (based upon surface roughness (Ra) and amplitude distribution function (ADF), peak count (PC) and bearing ratio (BR) curve).

Fine fibres with multifunctionality.

Co-drawing of metallic glass with polymers of similar viscosity–temperature behaviour enables highly uniform nanoscale cross-sectional features of various shapes in functional fibres without length limit.

Appearance feature enhancement for person re-identification

Person re-identification (Re-ID) has important practical application value in intelligent video analysis. Due to the illumination, occlusion, and pose variation, person Re-ID is still a challenging problem. Some recent Re-ID methods based on ResNet-50 have achieved high accuracy, but performance degradation is caused by pose variation. To address this issue, Pose-Invariant Convolutional Baseline (PICB) embed with the proposed Pooling Fusion Block (PFB) is put forward as a new baseline for person Re-ID task. On the basis of PICB, an end-to-end network named Appearance-Enhanced Feature Learning Network (AEFLN) is proposed to simultaneously learn diversity body features and discriminative part features. Specially, a novel (DBFL) strategy is presented to learn diversity body features, which could alleviate the potential local minima problem generated by optimizing model with randomly initialized parameters in PFB. In addition, uniform part-level feature extractors are applied to learn part features, which compensates for body features’ lack of distinguishable local information. In testing phase, body features and part features are integrated to represent the enhanced appearance feature for each person image. Comprehensive experiments have demonstrated that our method can outperform the sate-of-the-art results on several public available datasets, including Market-1501, CUHK03 and DukeMTMC-reID. For instance, we achieve 74.8% (+11.1%) and 76.5% (+19.0%) in Rank-1 accuracy and mAP on CUHK03 dataset.

Fabrication of piezoelectric thick-film stator using electrohydrodynamic jet printing for micro rotary ultrasonic motors

This paper proposes a lead zirconate titanate (PZT) thick-film piezoelectric microstator based on a high-performance PZT thick film fabricated by electrohydrodynamic jet (E-jet) printing. The PZT thick film element was printed directly on the elastic body from a PZT composite slurry to form the piezoelectric microstator. This fabrication process does not require conventional machining techniques such as thinning, bonding, and etching, and can be compatible with microelectromechanical systems (MEMS) technology. The printed PZT thick-film element exhibited compact and uniform features. The thick-film microstator produced a travelling wave with an amplitude of 345 nm, and the mechanical quality factor was found to be 736. The combination of E-jet printing and PZT thick-film technology simplified the manufacturing process and enhanced the performance of the piezoelectric stator, enabling the fabrication of a unique MEMS rotary ultrasonic motor device.

Layer-to-layer physical characteristics and compression behavior of 3D printed polymer metastructures fabricated using different process parameters

The extrusion-based three-dimensional printing technology such as fused deposition modeling (FDM) is the widely used one owing to its low cost. The FDM method can be used to fabricate parts with different fill densities, fill patterns, and process parameters such as extrusion temperature and print speed. In this research, influence of process parameters such as extrusion temperature and print speed on the physical characteristics such as the shape and the size of printed fibers in each layer, the fiber distance, and the fiber-to-fiber interface are investigated. In addition, their effects on mechanical characteristics of the printed samples are examined and interpreted with respect to the layer physical characteristics. To accomplish this, metastructure specimens were fabricated using acrylonitrile butadiene styrene polymer on a MakerBot 2X Replicator 3D printer. Three different extrusion temperatures (210, 230, and 250°C) and print speeds (100, 125, and 150 mm/s) were considered with an infill density of 50%. Optical microscopy was performed for layer physical characterization while the compression tests were done to evaluate the mechanical properties such as the failure strength, yield strength, and compressive modulus. It is observed that the print speed has minimal effect on mechanical properties; however, an improvement in mechanical properties is observed at higher fabrication temperature. Also, the lower fabrication temperature results in more uniform features within the layers as compared to those printed at higher extrusion temperature.

Determination of albedo parameters of the organometallic halide perovskite films

In this work, albedo number, energy and dose of the perovskite films were determined by the gamma ray spectrometry. The MAPbBr3-xClx, MAPbBr3-xIx, MAPbl3-xClx and MAPbl3 thin films were coated on the Pedot:PSS/ITO substrates by static spin coating technique. The structural properties of the films were determined with field emission scanning electron microscopy (FE-SEM) images and X-ray diffraction (XRD) patterns. Albedo parameters of perovskite films were carried out by using a high purity germanium detector with a resolution of 182 eV at 5.9 keV and 59.54 keV gamma-rays emitted from a radioactive source of Am241 (59.54 keV). In XRF experiments, the scattering angle was set 168°. XRD patterns show that perovskite structure has forming tetragonal with high crystallinity. Also, the perovskite layer has compact and high coverage capability and uniform surface feature in terms of FE-SEM morphology. It is observed that albedo parameters are dependent on the density, the mean atomic number and the average band gap energy of perovskite films. Also, high energy radiation scattering from the perovskite films appears to be enhanced significantly with the MABr treatment.

Identification of blood pressure reflecting personalized traits using bilateral photoplethysmography

BACKGROUND: Blood pressure (BP) is currently diagnosed by cuff-based devices, which are inconvenient and provide discontinuous measurements. Photoplethysmography (PPG)-based cuffless techniques have recently been used to accurately estimate both systolic BP (SBP) and diastolic BP (DBP). However, it is difficult to use these SBP and DBP estimations to reflect the personalized traits in the peripheral vascular condition; thus, their accuracy is limited.OBJECTIVE: The purpose of this study is to describe a technique that can be distinguished simply among three BP categories (normotensive, prehypertensive, and hypertensive) and reflect individual traits using PPG only.METHODS: We measured BP over 120 s using the fingers of 105 subjects. The PPG waveforms varied in size and amplitude over time. Therefore, normalization for uniform features for individual traits was done after the extracted waveforms were divided into multiple windows. The feature is determined by the lowest amplitude in the waveform within each divided window. The features have been applied to distinguish three BP categories using the first-eigenvector (1-EV) and second-eigenvector (2-EV) in linear discriminant analysis.RESULTS: The best decision boundary for each BP category was estimated using 1-EV (0.02 to 0.02) and 2-EV (0.02) in the hypertensive category, 1-EV ( 0) and 2-EV (0.02) in the prehypertensive category, and 1-EV (0.02) and 2-EV (0.02) in the normotensive category. The overlap range with 1-EV (0.02 to 0) and 2-EV (0.02) in particular accurately reflected individual traits.CONCLUSION: Discrimination among the three BP categories reflecting individual traits was successfully achieved using PPG. This method could improve limitations of cuff-based techniques.

Morphology controlled synthesis of ZnO nanoparticles for in-vitro evaluation of antibacterial activity

Abstract Novel hierarchical flower- and nanorod-shaped ZnO nanoparticles with uniform morphological features were successfully synthesized through controlled precipitation method in aqueous media without using any surfactant or template. To elucidate the growth mechanism of the synthesized nanoparticles, the effects of pH, reaction time and temperature were studied systematically. Selected ZnO samples were then subjected to SEM, FT-IR and XRD analysis. XRD patterns confirmed well crystalline nature of the as-synthesized powders. Furthermore, synthesized nanoparticles (hierarchical flowers as ZnO-1 and nanorods as ZnO-2), as well as commercial ZnO (ZnO-Com), were then investigated for in-vitro evaluation of antibacterial activity against various bacterial strains of clinical importance. Results showed that ZnO-2 exhibited higher antibacterial activity to all tested strains than ZnO-1, while ZnO-Com showed no antibacterial response in the applied experimental conditions. In addition, ZnO concentration-dependent antibacterial study unfolded that size of inhibition zones increased significantly from ~30 to 33 mm against Streptococcus mutans and from ~28 to 30 mm against Escherichia coli with increasing ZnO-2 concentration from 0.25 to 0.75 µg/µL. The present study, therefore, suggests that the application of synthesized ZnO nanoparticles as the antibacterial agent may be effective for inhibiting certain pathogenic bacteria in biomedical sides.

Remote Sensing Image Generation From Audio

Generating image from other modal data has attracted much attention in cross-modal studies, since the generated image offers intuitive vision information. Unlike the previous works which generate an image from text, a novel task is introduced, generating an image from audio. However, semantic gap intrinsically exists in cross-modal data, which disturbs the generative results. In order to explore the relevance between the audio and image, a novel reranking audio-image translation method is proposed. The proposed method: 1) maps the audio and image into a uniform feature space; 2) designs an audio-audio matching network to match the related audio; and 3) adopts an audio-image matching network for every matched audio to generate a related image, and the most frequent image is voted as the final result. Extensive experiments on two remote sensing cross-modal data sets demonstrate that the proposed method can visualize the content of audio.

Mining on Heterogeneous Manifolds for Zero-Shot Cross-Modal Image Retrieval

Most recent approaches for the zero-shot cross-modal image retrieval map images from different modalities into a uniform feature space to exploit their relevance by using a pre-trained model. Based on the observation that manifolds of zero-shot images are usually deformed and incomplete, we argue that the manifolds of unseen classes are inevitably distorted during the training of a two-stream model that simply maps images from different modalities into a uniform space. This issue directly leads to poor cross-modal retrieval performance. We propose a bi-directional random walk scheme to mining more reliable relationships between images by traversing heterogeneous manifolds in the feature space of each modality. Our proposed method benefits from intra-modal distributions to alleviate the interference caused by noisy similarities in the cross-modal feature space. As a result, we achieved great improvement in the performance of the thermal v.s. visible image retrieval task. The code of this paper: https://github.com/fyang93/cross-modal-retrieval

Finger vein biometric verification using block multi-scale uniform local binary pattern features and block two-directional two-dimension principal component analysis

Finger vein recognition has drawn increasing attention as one of the most popular and promising biometrics due to its high distinguishes ability, security and non-invasive procedure. The focus of this paper is on proposing new schemes based on finger vein patterns by employing block uniform local binary pattern and block two-directional two-dimension principal component analysis method in order to effectively reduce data redundancy. First, a block multi-scale uniform local binary pattern (MULBP) features operator based on improved circular neighborhood is employed to extract the local texture features of finger vein images effectively. Then two-directional two-dimension principal component analysis ((2D)2PCA) method is applied to finger vein recognition in this paper, which can effectively reduce the dimension of feature matrix and improve system performance. Furthermore, in order to avoid the disadvantage of (2D)2PCA method which cannot preserve some important local features, this paper adopts (2D)2PCA method based on block to preserve local information of image. The experimental results revealed that our proposed method achieved superior performance for the FV-USM finger vein database with a recognition rate of99.32 % and consistent performance for the Tianjin finger vein database with a recognition rate more than 99 %. Above results show that this new algorithm is effective and feasible in finger vein recognition system.