Neural network classifier and multiple hypothesis image segmentation for dietary assessment using calorie calculator

Nowadays, dietary assessment becomes the emerging system for evaluating the person’s food intake. In this paper, the multiple hypothesis image segmentation and feed-forward neural network classifier are proposed for dietary assessment to enhance the performance. Initially, the segmentation is applied to input image which is used to determine the regions where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the significant feature of food items is extracted by the global feature and local feature extraction method. After the features are obtained, the classification is performed for each segmented region using feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food area volume and (ii) calorie and nutrition measure based on mass value. The outcome of the proposed method attains 96% of accuracy value which provides the better classification performance.     

Spontaneously Embedded Scattering Structures in a Flexible Substrate for Light Extraction

A flexible hazy substrate (FHS) with embedded air bubbles to increase light extraction efficiency of organic light‐emitting diodes (OLEDs) is reported. In order to embed the air bubbles in the flexible substrate, micropatterned substrates are fabricated by plasma treatment, and then coated with a planarization layer. During the planarization layer coating, air bubbles are trapped between the substrate and the planarization layer. The haze of the FHS can be controlled from 1.7% to 68.4% by changing the size of micropatterns by adjusting the plasma treatment time. The FHS shows average haze of 68.4%, average total transmittance of 90.3%, and extremely flat surface with average roughness (R _a) of 1.2 nm. Rigorous coupled‐wave analysis and finite‐difference time‐domain simulations are conducted to demonstrate that the air bubbles in the substrate can effectively extract photons that are trapped in the substrate. The FHS increases the power efficiency of OLEDs by 22% and further increases by 91% combined with an external extraction layer. Moreover, the FHS has excellent mechanical flexibility. No defect has been observed after 10 000 bending cycles at bending radius of 4 mm.     

Broadband Light Absorption and Efficient Charge Separation Using a Light Scattering Layer with Mixed Cavities for High‐Performance Perovskite Photovoltaic Cells with Stability

CH₃NH₃PbI₃ is one of the promising light sensitizers for perovskite photovoltaic cells, but a thick layer is required to enhance light absorption in the long‐wavelength regime ranging from PbI₂ absorption edge (500 nm) to its optical band‐gap edge (780 nm) in visible light. Meanwhile, the thick perovskite layer suppresses visible‐light absorption in the short wavelengths below 500 nm and charge extraction capability of electron–hole pairs produced upon light absorption. Herein, we find that a new light scattering layer with the mixed cavities of sizes in 100 and 200 nm between transparent fluorine‐doped tin oxide and mesoporous titanium dioxide electron transport layer enables full absorption of short‐wavelength photons (λ < 500 nm) to the perovskite along with enhanced absorption of long‐wavelength photons (500 nm < λ < 780 nm). Moreover, the light‐driven electric field is proven to allow efficient charge extraction upon light absorption, thereby leading to the increased photocurrent density as well as the fill factor prompted by the slow recombination rate. Additionally, the photocurrent density of the cell with a light scattering layer of mixed cavities is stabilized due to suppressed charge accumulation. Consequently, this work provides a new route to realize broadband light harvesting of visible light for high‐performance perovskite photovoltaic cells.     

A particle‐based moving interface method (PMIM) for modeling the large deformation of boundaries in soft matter systems

The mechanics of the interaction between a fluid and a soft interface undergoing large deformations appear in many places, such as in biological systems or industrial processes. We present an Eulerian approach that describes the mechanics of an interface and its interactions with a surrounding fluid via the so‐called Navier boundary condition. The interface is modeled as a curvilinear surface with arbitrary mechanical properties across which discontinuities in pressure and tangential fluid velocity can be accounted for using a modified version of the extended finite element method. The coupling between the interface and the fluid is enforced through the use of Lagrange multipliers. The tracking and evolution of the interface are then handled in a Lagrangian step with the grid‐based particle method. We show that this method is ideal to describe large membrane deformations and Navier boundary conditions on the interface with velocity/pressure discontinuities. The validity of the model is assessed by evaluating the numerical convergence for a axisymmetrical flow past a spherical capsule with various surface properties. We show the effect of slip length on the shear flow past a two‐dimensional capsule and simulate the compression of an elastic membrane lying on a viscous fluid substrate. Copyright © 2015 John Wiley & Sons, Ltd.     

Powell–Sabin B‐splines and unstructured standard T‐splines for the solution of the Kirchhoff–Love plate theory exploiting Bézier extraction

The equations that govern Kirchhoff–Love plate theory are solved using quadratic Powell–Sabin B‐splines and unstructured standard T‐splines. Bézier extraction is exploited to make the formulation computationally efficient. Because quadratic Powell–Sabin B‐splines result in ‐continuous shape functions, they are of sufficiently high continuity to capture Kirchhoff–Love plate theory when cast in a weak form. Unlike non‐uniform rational B‐splines (NURBS), which are commonly used in isogeometric analysis, Powell–Sabin B‐splines do not necessarily capture the geometry exactly. However, the fact that they are defined on triangles instead of on quadrilaterals increases their flexibility in meshing and can make them competitive with respect to NURBS, as no bending strip method for joined NURBS patches is needed. This paper further illustrates how unstructured T‐splines can be modified such that they are ‐continuous around extraordinary points, and that the blending functions fulfil the partition of unity property. The performance of quadratic NURBS, unstructured T‐splines, Powell–Sabin B‐splines and NURBS‐to‐NURPS (non‐uniform rational Powell–Sabin B‐splines, which are obtained by a transformation from a NURBS patch) is compared in a study of a circular plate. Copyright © 2015 John Wiley & Sons, Ltd.     

Automated detection of glioblastoma tumor in brain magnetic imaging using ANFIS classifier

This article proposes a novel and efficient methodology for the detection of Glioblastoma tumor in brain MRI images. The proposed method consists of the following stages as preprocessing, Non‐subsampled Contourlet transform (NSCT), feature extraction and Adaptive neuro fuzzy inference system classification. Euclidean direction algorithm is used to remove the impulse noise from the brain image during image acquisition process. NSCT decomposes the denoised brain image into approximation bands and high frequency bands. The features mean, standard deviation and energy are computed for the extracted coefficients and given to the input of the classifier. The classifier classifies the brain MRI image into normal or Glioblastoma tumor image based on the feature set. The proposed system achieves 99.8% sensitivity, 99.7% specificity, and 99.8% accuracy with respect to the ground truth images available in the dataset.     

Prospects of Supercritical Fluids in Realizing Graphene‐Based Functional Materials

Supercritical‐fluids science and technology predate all the approaches that are currently established for graphene production by several decades in advanced materials design. However, it has only recently been proposed as a plausible approach for graphene processing. Since then, supercritical fluids have emerged into contention as an alternative to existing technologies because of their scalability and versatility in processing graphene materials, which include composites, aerogels, and foams. Here, an overview is presented of such materials prepared through supercritical fluids from an advanced materials science standpoint, with a discussion on their fundamental properties and technological applications. The benefits of supercritical‐fluid processing over conventional liquid‐phase processing are presented. The benefits include not only better performances for advanced applications but also environmental issues associated with the synthesis process. Nevertheless, the limitations of supercritical‐fluid processing are also stressed, along with challenges that are still faced toward the achievement of the great expectations from graphene materials.     

小波包能熵谱和证据融合推理的电梯急停诊断

采用加速度时域信号的峭度系数和小波包变换后的频域信号能熵谱定义特征向量,获得证据融合法推理证据;利用测试样本统计得到特征值区间数;基于待测样本特征值与区间数之间的距离设计相似度,并归一化得到证据的基本概率分配函数;而后对证据进行时空融合得到证据融合合成规则,并采用可信度分配函数进行证据融合推理诊断;最后开展电梯实测实验,利用3层sym8小波包变换和9个证据对急停进行诊断。实验表明,该方法电梯急停故障诊断的准确率大于98%。