Application of Vis–NIR hyperspectral imaging in classification between fresh and frozen-thawed pork Longissimus Dorsi muscles

Fresh and frozen-thawed (F-T) pork meats were classified by Vis–NIR hyperspectral imaging. Eight optimal wavelengths (624, 673, 460, 588, 583, 448, 552 and 609 nm) were selected by successive projections algorithm (SPA). The first three principal components (PCs) obtained by principal component analysis (PCA) accounted for over 99.98% of variance. Gray-level-gradient co-occurrence matrix (GLGCM) was applied to extract 45 textural features from the PC images. The correct classification rate (CCR) was employed to evaluate the performance of the partial least squares-discriminate analysis (PLS-DA) models, by using (A) the reflected spectra at full wavelengths and (B) those at the optimal wavelengths, (C) the extracted textures based on the PC images, and (D) the fused variables combining spectra at the optimal wavelengths and textures. The results showed that the best CCR of 97.73% was achieved by applying (D), confirming the high potential of textures for fresh and F-T meat discrimination.     

Solidification morphology and phase selection in drop-tube processed Ni–Fe–Si intermetallics

Drop-tube processing was used to rapidly solidify droplets of Ni_64.7Fe₁₀Si_25.3 and Ni_59.7Fe₁₅Si_25.3 alloys. In the larger droplets, and therefore at low cooling rates, only two phases, γ-Ni₃₁Si₁₂ and β₁-Ni₃Si were observed. Conversely, in the smaller droplets, and therefore at higher cooling rates, the metastable phase Ni₂₅Si₉ was also observed. The critical cooling rate for the formation of Ni₂₅Si₉ was estimated as 5 × 10³ K s⁻¹. SEM and TEM analysis reveals three typical microstructures: (I) a regular structure, comprising single-phase γ-Ni₃₁Si₁₂ and a eutectic structure between γ-Ni₃₁Si₁₂ and β₁-Ni₃Si; (II) a refined lamellar structure with a lamellar spacing <50 nm comprising γ-Ni₃₁Si₁₂ and β₁-Ni₃Si; (III) an anomalous structure with a matrix of Ni₂₅Si₉ and only a very small proportion of a second, and as yet unidentified, phase. These results indicate that there is an extended stability field for Ni₂₅Si₉ in the Ni-rich part of the Ni–Fe–Si ternary system in comparison to the Ni–Si binary system. With an increase of cooling rate, an increasing fraction of small droplets experience high undercoolings and, therefore, can be undercooled into the Ni₂₅Si₉ stability field forming droplets consisting of only the anomalous structure (III). The Fe atoms are found to occupy different substitutional sites in different phase, i.e. Fe substitutes for Ni in the γ phase and Si in the L1₂ (β₁) phase respectively.     

基于注意力机制与文本信息的用户关系抽取

随着社交媒体的发展,用户之间的关系网络对于社交媒体的分析有很大的帮助。因此,该文主要研究用户好友关系检测。以往的关于用户好友关系抽取的研究主要基于社交媒体上的结构化信息,比如其他好友关系,用户的不同属性等。但是,很多时候用户本身并没有大量的好友信息存在,同时也不一定有很多确定的属性。因此,我们希望基于用户发表的文本信息来对用户关系进行预测。不同于以往的潜在好友推荐算法,该文提出了一种基于注意力机制以及长短时记忆网络(long short-term memory,LSTM)的好友关系预测模型,将好友之间的评论分开处理,通过分析用户之间的评论来判断是否具备一定的好友关系。该模型将好友双方信息拼接后的结果作为输入,并将注意力机制应用于LSTM的输出。实验表明,用户之间的评论对于好友关系预测确实有较大的实际意义,该文提出的模型较之于多个基准系统的效果,取得了明显的提升。在不加入任何其它非文本特征的情况下,实验结果的准确率达到了77%。     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

An iterative method for suboptimal control of linear time-delayed systems

This article presents a new approach for solving the Optimal Control Problem (OCP) of linear time-delay systems with a quadratic cost functional. The proposed method can also be used for designing optimal control time-delay systems with disturbance. In this study, the Variational Iteration Method (VIM) is employed to convert the original Time-Delay Optimal Control Problem (TDOCP) into a sequence of nonhomogeneous linear two-point boundary value problems (TPBVPs). The optimal control law obtained consists of an accurate linear feedback term and a nonlinear compensation term which is the limit of an adjoint vector sequence. The feedback term is determined by solving Riccati matrix differential equation. By using the finite-step iteration of a nonlinear compensation sequence, we can obtain a suboptimal control law. Finally, Illustrative examples are included to demonstrate the validity and applicability of the technique.     

Static stress analysis of carbon nano-tube reinforced composite (CNTRC) cylinder under non-axisymmetric thermo-mechanical loads and uniform electro-magnetic fields

Static stresses analysis of carbon nano-tube reinforced composite (CNTRC) cylinder made of poly-vinylidene fluoride (PVDF) is investigated in this study. Non-axisymmetric thermo-mechanical loads are applied on cylinder in presence of uniform longitudinal magnetic field and radial electric field. The surrounded elastic medium is modeled by Pasternak foundation because of its advantages to the Winkler type. Distribution of radial, circumferential and effective stresses, temperature field and electric displacements in CNTRC cylinder are determined based on Mori–Tanaka theory. The detailed parametric study is conducted, focusing on the remarkable effects of magnetic field intensity, elastic medium, angle orientation and volume fraction of carbon nano-tubes (CNTs) on distribution of effective stress. Results demonstrated that fatigue life of CNTRC cylinder will be significantly dependent on magnetic intensity, angle orientation and volume fraction of CNTs. Results of this research can be used for optimum design of thick-walled cylinders under multi-physical fields.     

Microstructure and mechanical properties of an Al–TiC metal matrix composite obtained by reactive synthesis

A metal matrix composite has been obtained by a novel synthesis route, reacting Al₃Ti and graphite at 1000 °C for about 1 min after ball-milling and compaction. The resulting composite is made of an aluminium matrix reinforced by nanometer sized TiC particles (average diameter 70 nm). The average TiC/Al ratio is 34.6 wt.% (22.3 vol.%). The microstructure consists of an intimate mixture of two domains, an unreinforced domain made of the Al solid solution with a low TiC reinforcement content, and a reinforced domain. This composite exhibits uncommon mechanical properties with regard to previous micrometer sized Al–TiC composites and to its high reinforcement volume fraction, with a Young’s modulus of ∼110 GPa, an ultimate tensile strength of about 500 MPa and a maximum elongation of 6%.     

Hygrothermal deformation of orthotropic nanoplates based on the state-space concept

This paper deals with the investigation of the effect of hygrothermal conditions on the bending of nanoplates using Levy type solution model employing the state-space concept. The nanoplates are assumed to be subjected to a hygrothermal environment. The two-unknown function plate theory is used to derive the governing differential equations on the basis of Eringen's nonlocal elasticity theory. The governing equations contain the small scale effect as well as hygrothermal and mechanical effects. These equations are converted into a set of first-order linear ordinary differential equations with constant coefficients. Analytical solution of bending response for nanoplates under combinations of simply supported, clamped and free boundary conditions is obtained. Comparison of the results with those being in the open literature is made. The influences played by small scale parameter, temperature rise, the degree of moisture concentration, boundary conditions, plate aspect ratio and side-to-thickness ratio are studied.     

基于感知评价的Internet语音终端流量控制

分析了影响因特网语音通信质量的主要因素，根据实时传输控制协议计算延迟、丢包率等网络参数，并利用RBF神经网络将参数映射为语音质量评分，根据评分值的变化动态地调整语音终端的编码速率，在保证一定语音质量的同时，缓解网络拥塞。实验证明了该方法的有效性。