Effects Of Dimensions Research Articles

Phthalocyanine Covalent Organic Frameworks: Dimensionality Effect on Third‐Order Nonlinear Optical Properties

AbstractDimensionality of covalent organic frameworks (COFs), in terms of 2D and 3D, must greatly influence their properties and functionalities due to the different electronic and porous structures, but still less investigated in the 20 years history. Herein, on the basis of the imidization reaction of phthalocyanine‐based tetraanhydride monomers with either 1,4‐phenylenediamine or 1,3,5,7‐tetra(4‐aminophenyl)adamantine, 2D and 3D imide‐bonded COFs with sql and pts topology have been prepared to explore their third‐order nonlinear optical (NLO) properties. In contrast to metal‐free analogues, both 2D and 3D copper‐phthalocyanine COFs have the enhanced NLO behaviors according to the open aperture Z‐scan and optical limiting (OL) results recorded under a nanosecond laser at 532 nm. In particular, 2D COFs with strong π–π staking phthalocyanine units show the NLO property with bigger third‐order nonlinear susceptibility (Imχ(3)) and unique reverse saturation absorption response at 1064 nm than that of 3D species with dispersed conjugated modules. Furthermore, femtosecond transient absorption spectra disclose the longer excited lifetimes of copper COFs than metal free samples, helpful in their NLO property. These findings clearly disclose the materials advantages of 2D phthalocyanine COFs toward the NLO characteristics and provide new candidates for OL application.

Superradiant pulse saturation in a Free Electron Laser

A study is made of the saturation mechanism of a single superradiant ‘spike’ of radiation in a Free Electron Laser. A one-dimensional (1D) computer model is developed using the Puffin, un-averaged FEL simulation code, which allows sub-radiation wavelength evolution of both the spike radiation field and the electron dynamics to be modelled until the highly non-linear saturation process of the spike is observed. Animations of the process from the start to the end of the interaction are available. The resultant saturated spike duration is at the sub-wavelength scale and has a broad spectrum. The electrons passing through the spike can both lose and gain energy many times greater than that of the ‘normal’ non-pulsed FEL interaction. A saturation mechanism is proposed and tested via a simple analysis of the 1D FEL equations. The scaling results of the analysis are seen to be in good agreement with the numerical results. A simple model of three dimensional diffraction effects of the radiation is applied to the results of the 1D simulations. This greatly reduces longer wavelengths of the power spectrum, which are seen to be emitted mainly after the electrons have propagated through the spike, and is seen to be in qualitative agreement with recent experimental results.

A study of dimensional effects on the stress characteristics of Yunnan pine shafts considering seismic strain rates

Abstract The mechanical properties of wood are affected by member size and loading rate. Axial compression tests with different seismic strain rates and sizes of specimens were carried out to investigate the static and dynamic dimensional effects of Yunnan pine timber. And obtained load-displacement curves, compressive strength, modulus of elasticity, peak strain and Poisson’s ratio. Weibull’s weakest chain theory, Bazant’s law of dimensional effects and Carpinteri’s law of multiple fractal dimensional effects were used to analyze the dimensional effects on the compressive strength of wood, and to establish a wood strength model that takes strain rate effects and dimensional effects into account. The results showed that the compressive strength, elastic modulus, and Poisson’s ratio of Yunnan pine wood exhibit both size and strain rate effects. Under the coupling effect of strain rate effect and size effect, the size effect of Yunnan pine wood strength decreases with increasing strain rate, while the strain rate effect increases with increasing size. A size effect model for compressive strength of wood considering strain rate effect based on three theories and experimental data can well describe the dynamic size effect of Yunnan pine wood strength.

Highly Robust Room-Temperature Interfacial Ferromagnetism in Ultrathin Co2Si Nanoplates.

The reduced dimensionality and interfacial effects in magnetic nanostructures open the feasibility to tailor magnetic ordering. Here, we report the synthesis of ultrathin metallic Co2Si nanoplates with a total thickness that is tunable to 2.2 nm. The interfacial magnetism coupled with the highly anisotropic nanoplate geometry leads to strong perpendicular magnetic anisotropy and robust hard ferromagnetism at room temperature, with a Curie temperature (TC) exceeding 950 K and a coercive field (HC) > 4.0 T at 3 K and 8750 Oe at 300 K. Theoretical calculations suggest that ferromagnetism originates from symmetry breaking and undercoordinated Co atoms at the Co2Si and SiO2 interface. With protection by the self-limiting intrinsic oxide, the interfacial ferromagnetism of the Co2Si nanoplates exhibits excellent environmental stability. The controllable growth of ambient stable Co2Si nanoplates as 2D hard ferromagnets could open exciting opportunities for fundamental studies and applications in Si-based spintronic devices.

Dimensional Fidelity and Orientation Effects of PolyJet Technology in 3D Printing of Negative Features for Microfluidic Applications.

Negative features in microdevices find a wide range of applications. The process of 3D printing has revolutionized their fabrication due to the combination of good resolution and integration capability. Herein, we report on a systematic study of the effects of materials and print directions on the 3D printing of microfluidic channels as negative features under PolyJet technology. Specifically, the Statasys Objet500 printer was used for this study. We printed two sets of chips (n=10 each), each of which contains channel pairs of a high-contrast reference material and a sacrificial material, respectively. Both materials were embedded in a clear photopolymer resin. The channel pairs ranged in planned width from 64 to 992 μm. To explore the effect on print orientation, channels were printed either parallel or perpendicular with respect to the jetting head's movement. The width of each channel of a pair was compared for each planned width and each combination of materials. The effect of print orientation on channel morphology was also investigated. We found that reproducibility and accuracy were highest at a planned channel width of approximately ≥600 μm and that channel morphology was most suitable when the jetting head of the printer moved parallel to the channel's longitudinal axis. The results should be of interest to any users who wish to create negative features using PolyJet 3D technology.

КВАНТОВЫЙ РАЗМЕРНЫЙ ЭФФЕКТ В ЧИСТЫХ ПЛЕНКАХ АЛЮМИНИЯ

In the modern world, there's a notable trend towards the active miniaturization of electronic devices. With technological advances enabling the manipulation of nanostructures, there's an increasing focus on exploring quantum effects pivotal to such designs. One distinguishing feature of nanostructures is the quantum nature of the electron's energy spectrum. This spectrum becomes discrete in directions where electrons move. Depending on the direction of this confinement, structures can be categorized as nanoplates, quantum wires, or quantum dots. The properties of such structures can significantly differ from those observed in large-scale systems. When discussing superconductivity, particular emphasis is placed on its macroscopic quantum properties.The influence on electronic wave functions is reflected in the characteristics of the superconducting state on broader scales. The Bardeen-Cooper-Schrieffer (BCS) theory is frequently utilized to analyze these nanostructures. The Gor’kov equations method serves as a potent tool for tasks related to the BCS theory. For instance, it can determine the parameters of the superconducting state, critical temperature, and current. Components of these equations, like Green's functions, are associated with various system properties. Research in the early stages of superconductivity studies revealed that the critical temperature (Tc ) – the temperature at which a material transitions to a superconducting state – can differ significantly between thin films and bulk materials. Intriguingly, reducing the film's thickness can both decrease (e.g., in niobium) and increase (e.g., in aluminum) the Tc value. This study delves into the quantum size effect in thin aluminum films, paving the way for materials with higher transition temperatures. Such advancements can simplify and make the maintenance of superconducting systems more cost-effective. In this study, a theoretical relationship between the critical temperature of a thin aluminum film and its thickness was derived. The Green's function method was chosen, which hadn't been previously employed for this computation. This approach offers greater potential compared to other superconductivity theory methods, presenting extensive avenues for theoretical exploration in this domain. The authors are confident that this work will contribute to further research on quantum dimensional effects in low-dimensional superconducting structures.

Theory of nonlocal modal hydrodynamic functions for beam and plate vibrations in viscous fluids

In this paper, we introduce a new nonlocal modal hydrodynamic theory for fluid–structure interactions (FSI) of light, flexible cantilever beams and plates undergoing small amplitude vibrations in Newtonian, incompressible, viscous, heavy fluids otherwise at rest. For low aspect ratio flexible structures and high mode numbers, three dimensional (3D) and nonlocal fluid effects become prominent drivers of the coupled dynamics, to the point that existing local hydrodynamic theories based on two dimensional (2D) fluid approximations become inadequate to predict the system response. On the other hand, our approach is based on a rigorous, yet efficient, 3D treatment of the hydrodynamic loading on cantilevered thin structures. The off-line solution of the FSI problem results in the so-called nonlocal modal hydrodynamic function matrix, that is, the representation of the nonlocal hydrodynamic load operator on a basis formed by the structural modes. Our theory then integrates the nonlocal hydrodynamics within a fully coupled structural modal model in the frequency domain. We compare and discuss our theory predictions in terms of frequency response functions, mode shapes, hydrodynamic loads, quality factors, added mass ratios with the predictions of the classical local approaches, for different actuation scenarios, identifying the limitations of the hypotheses underlying existing treatments. Importantly, we also validate our new model with experiments conducted on flexible square plates. While computationally efficient, our fully coupled theory is exact up to numerical truncation and can bridge knowledge gaps in the design and analysis of FSI systems based on low aspect ratio flexible beams and plates.

Spectrally Segmented-Enhanced Neural Network for Precise Land Cover Object Classification in Hyperspectral Imagery

The paradigm shift brought by deep learning in land cover object classification in hyperspectral images (HSIs) is undeniable, particularly in addressing the intricate 3D cube structure inherent in HSI data. Leveraging convolutional neural networks (CNNs), despite their architectural constraints, offers a promising solution for precise spectral data classification. However, challenges persist in object classification in hyperspectral imagery or hyperspectral image classification, including the curse of dimensionality, data redundancy, overfitting, and computational costs. To tackle these hurdles, we introduce the spectrally segmented-enhanced neural network (SENN), a novel model integrating segmentation-based, multi-layer CNNs, SVM classification, and spectrally segmented dimensionality reduction. SENN adeptly integrates spectral–spatial data and is particularly crucial for agricultural land classification. By strategically fusing CNNs and support vector machines (SVMs), SENN enhances class differentiation while mitigating overfitting through dropout and early stopping techniques. Our contributions extend to effective dimensionality reduction, precise CNN-based classification, and enhanced performance via CNN-SVM fusion. SENN harnesses spectral information to surmount challenges in “hyperspectral image classification in hyperspectral imagery”, marking a significant advancement in accuracy and efficiency within this domain.

DLAN:Modeling user long- and short-term preferences based on double-layer attention network for next point-of-interest recommendation

The next Point-of-Interest (POI) recommendation, in recent years, has attracted an extensive amount of attention from the academic community. RNN-based methods cannot establish effective long-term dependencies among the input sequences when capturing the user’s motion patterns, resulting in inadequate exploitation of user preferences. Besides, the majority of prior studies often neglect high-order neighborhood information in users’ check-in trajectory and their social relationships, yielding suboptimal recommendation efficacy. To address these issues, this paper proposes a novel Double-Layer Attention Network model, named DLAN. Firstly, DLAN incorporates a multi-head attention module that can combine first-order and high-order neighborhood information in user check-in trajectories, thereby effectively and parallelly capturing both long- and short-term preferences of users and overcoming the problem that RNN-based methods cannot establish long-term dependencies between sequences. Secondly, this paper designs a user similarity weighting layer to measure the influence of other users on the target users leverage the social relationships among them. Finally, comprehensive experiments are conducted on user check-in data from two cities, New York (NYC) and Tokyo (TKY), and the results demonstrate that DLAN achieves a performance in Accuracy and Mean Reverse Rank enhancement by 8.07% -36.67% compared to the state-of-the-art method. Moreover, to investigate the effect of dimensionality and the number of heads of the multi-head attention mechanism on the performance of the DLAN model, we have done sufficient sensitivity experiments.

Dimensional scaling effects on critical current density and magnetization switching in CoFeB-based magnetic tunnel junction

In this work, we theoretically investigate the size dependence of the magnetization reversal behavior in CoFeB-MgO-CoFeB magnetic tunnel junctions (MTJs) by employing an atomistic spin model coupled with the spin accumulation model. The former and the latter are used to construct the magnetic structure and to model the spin transport behavior, respectively. The accuracy of the approach is confirmed by investigating the dependence of the magnetic properties on the size of the MTJ. Perpendicular magnetic anisotropy (PMA) is observed for thickness less than 1.3 nm, which is in an excellent agreement with experiment. To investigate the magnetization dynamics induced by spin-polarized current, a charge current is injected into the MTJ structure perpendicular to the stack leading to a spin-transfer torque acting on the magnetization of the CoFeB layer. The results show that the critical current density to reverse the magnetization is lower for PMA-MTJ and in addition for the same injected current density the time required to switch the magnetization is shorter than for an in-plane MTJ. The results can be used as a guideline to optimize the design of high performance MTJs for STT-MRAM applications.

Phase diagram of muonium hydride: the significant effect of dimensionality

We carry out a theoretical investigation of the low-temperature phase diagram of muonium hydride in two dimensions, using numerical simulations. It is shown that the phase diagram of this substance is qualitatively different in two and three dimensions. Specifically, while in three dimensions it is essentially identical to that of parahydrogen, i.e., only displaying a single (crystalline) phase. In two dimensions it is very similar to that of 4He, with an equilibrium liquid phase that turns superfluid at a temperature as high as ∼2.2 K, and crystallizes under applied pressure. This is a well-described case of a continuous-space condensed matter system whose ground state equilibrium phase is qualitatively altered by dimensional reduction.

Evaluation‐Number Constrained Optimization Problem and its Solution Strategy

This paper addresses optimization problems subject to an objective function's evaluation‐number constraint arbitrarily given in advance. These problems are practical for black‐box objective functions which cost much money and/or time per evaluation because money and/or time constraints are typically applicable in real‐world projects. This paper suggests a new solution strategy that can be used to adapt metaheuristics to evaluation‐number constraints arbitrarily given in advance. The proposed strategy updates the setting parameters of a target metaheuristic algorithm for every generation by solving a fixed small‐size optimization problem related to the evaluation‐number constraint. It has the advantage of being insensitive to the effects of dimensionality increases in principle. The effectiveness of the proposed strategy is confirmed by numerical experiments with two well‐known metaheuristics, i.e., the particle swarm optimization algorithm and the differential evolution algorithm. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

Ultrathin Limit on the Anisotropic Superconductivity of Single-Layered Cuprate Films

Exploring dimensionality effects on cuprates is important for understanding the nature of high-temperature superconductivity. By atomically layer-by-layer growth with oxide molecular beam epitaxy, we demonstrate that La2–x Sr x CuO4 (x = 0.15) thin films remain superconducting down to 2 unit cells of thickness but quickly reach the maximum superconducting transition temperature at and above 4 unit cells. By fitting the critical magnetic field (μ 0 H c2), we show that the anisotropy of the film’s superconductivity increases with decreasing film thickness, indicating that the superconductivity of the film gradually evolves from weak three- to two-dimensional character. These results are helpful to gain more insight into the nature of high-temperature superconductivity with dimensionality.

A feature selection method based on the Golden Jackal-Grey Wolf Hybrid Optimization Algorithm.

This paper proposes a feature selection method based on a hybrid optimization algorithm that combines the Golden Jackal Optimization (GJO) and Grey Wolf Optimizer (GWO). The primary objective of this method is to create an effective data dimensionality reduction technique for eliminating redundant, irrelevant, and noisy features within high-dimensional datasets. Drawing inspiration from the Chinese idiom "Chai Lang Hu Bao," hybrid algorithm mechanisms, and cooperative behaviors observed in natural animal populations, we amalgamate the GWO algorithm, the Lagrange interpolation method, and the GJO algorithm to propose the multi-strategy fusion GJO-GWO algorithm. In Case 1, the GJO-GWO algorithm addressed eight complex benchmark functions. In Case 2, GJO-GWO was utilized to tackle ten feature selection problems. Experimental results consistently demonstrate that under identical experimental conditions, whether solving complex benchmark functions or addressing feature selection problems, GJO-GWO exhibits smaller means, lower standard deviations, higher classification accuracy, and reduced execution times. These findings affirm the superior optimization performance, classification accuracy, and stability of the GJO-GWO algorithm.

Effect of dimensionality on the excitation wavelength dependence of the Fano-Raman line-shape: a brief review.

The already existing heterogeneity in nanomaterials makes it an intriguing yet complex system to study size effect vis-à-vis other external perturbations and thereby local modifications at the nanoscale, thus demanding an improved tool and analysis for the choice of study. The analysis of existential subtle perturbations and interactions in a wide class of materials using Raman spectromicroscopy has proved to be of utmost importance, and various phenomena such as quantum confinement and its interplay with Fano resonance have already been investigated in nanomaterials, including the role of various perturbations such as temperature, pressure, doping, bias, and excitation wavelength on Raman spectral line shape parameters. Amongst different perturbations that cause a change in the spectral profile of Fano resonance, the gray area of wavelength dependence of Fano Raman line shape profiles has been least analysed in the literature. Moreover, the true signature of Fano resonance in nanoscaled systems, which is the wavelength dependence of Fano interaction, remains the least discussed. This review summarises the wavelength dependent correlation of Fano resonance and its effect on the Raman spectral line-shape parameters in some bulk materials, nanomaterials, and molecular systems involving heavily doped p-type crystalline silicon, 2-D MoS2, graphene, WS2, single walled carbon nanotubes, etc. A brief overview of Fano resonance in metamaterials and photonic systems is also provided.

MFILS: Tri-Selection via Convex and Nonconvex Regularizations.

In many real-world applications, data are represented by multiple instances and simultaneously associated with multiple labels. These data are always redundant and generally contaminated by different noise levels. As a result, several machine learning models fail to achieve good classification and find an optimal mapping. Feature selection, instance selection, and label selection are three effective dimensionality reduction techniques. Nevertheless, the literature was limited to feature and/or instance selection but has, to some extent, neglected label selection, which also plays an essential role in the preprocessing step, as label noises can adversely affect the performance of the underlying learning algorithms. In this article, we propose a novel framework termed multilabel Feature Instance Label Selection (mFILS) that simultaneously performs feature, instance, and label selections in both convex and nonconvex scenarios. To the best of our knowledge, this article offers, for the first time ever, a study using the triple and simultaneous selection of features, instances, and labels based on convex and nonconvex penalties in a multilabel scenario. Experimental results are built on some known benchmark datasets to validate the effectiveness of the proposed mFILS.

DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs

Dynamic graph embedding has gained great attention recently due to its capability of learning low-dimensional and meaningful graph representations for complex temporal graphs with high accuracy. However, recent advances mostly focus on learning node embeddings as deterministic "vectors" for static graphs, hence disregarding the key graph temporal dynamics and the evolving uncertainties associated with node embedding in the latent space. In this work, we propose an efficient stochastic dynamic graph embedding method (DynG2G) that applies an inductive feedforward encoder trained with node triplet energy-based ranking loss. Every node per timestamp is encoded as a time-dependent probabilistic multivariate Gaussian distribution in the latent space, and, hence, we are able to quantify the node embedding uncertainty on-the-fly. We have considered eight different benchmarks that represent diversity in size (from 96 nodes to 87 626 and from 13 398 edges to 4 870 863) as well as diversity in dynamics, from slowly changing temporal evolution to rapidly varying multirate dynamics. We demonstrate through extensive experiments based on these eight dynamic graph benchmarks that DynG2G achieves new state-of-the-art performance in capturing the underlying temporal node embeddings. We also demonstrate that DynG2G can simultaneously predict the evolving node embedding uncertainty, which plays a crucial role in quantifying the intrinsic dimensionality of the dynamical system over time. In particular, we obtain a "universal" relation of the optimal embedding dimension, Lo , versus the effective dimensionality of uncertainty, Du , and infer that Lo=Du for all cases. This, in turn, implies that the uncertainty quantification approach we employ in the DynG2G algorithm correctly captures the intrinsic dimensionality of the dynamics of such evolving graphs despite the diverse nature and composition of the graphs at each timestamp. In addition, this L0 - Du correlation provides a clear path to selecting adaptively the optimum embedding size at each timestamp by setting L ≥ Du .

Improved Multi-Distance ARMF Integrated With LTSA Based Pattern Matching Method and Its Application in Fault Diagnosis

Effective dimensionality reduction (DR) and classification in fault diagnosis remain a significant challenge, primarily due to the increasing scale of industrial processes and the non-linear and high-dimensional features of process data. To address this challenge, we present local tangent space alignment (LTSA) integrated with a multi-distance adaptive order morphological filter (MARMF) fault diagnosis method (LTSA-MARMF). In LTSA-MARMF, LTSA that preserves the local manifold structure using tangent space is first utilized for DR to provide the required feature space data for ARMF. Next, the cosine distance and dynamic time warping distance are introduced into the distance error of ARMF, considering the spatial similarity and dynamic features to improve classification accuracy. Finally, the distance-matching result of the pattern is applied to determine the type of fault. Through simulations, it is evident that LTSA-MARMF can achieve more satisfactory fault diagnosis accuracy than other related methods on the Tennessee-Eastman process (TEP) and the actual Grid-connected PV System (GPVS). <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is inspired by the difficult-to-handle high-dimensional and non-linear features of process data but is also applicable to high-dimensional and non-linear data from other industrial processes. The DR and classification are important aspects of fault diagnosis. In this paper, a novel pattern-matching method is utilized for fault diagnosis, which uses LTSA and the modified multi-distance ARMF for DR and classification, respectively. In terms of mathematics, the distance error of ARMF is analyzed. The combination of multi-distance is used to enhance the accuracy of fault diagnosis. The preliminary experiments show that LTSA-MARMF is feasible, but has not been tested in the plant. We will consider testing LTSA-MARMF in an actual plant in future research.

Exploring the Problems and Countermeasures in the Practice of Elderly Wisdom Sports Services in Anhui Province Based on Principal Component Analysis Methods

Abstract With the continuous progress and broad application of cutting-edge information technology such as big data, cloud computing, virtual reality and artificial intelligence, senior sports services has ushered in unprecedented development opportunities, especially the rise of senior intelligent sports services. In this study, we applied the principal component analysis method to conduct in-depth screening of evaluation indexes to assess the quality of the practice of senior intelligent sports services in Anhui Province. Through the comprehensive analysis of the eigenroots and the contribution ratio of variance, this paper successfully identified the key factors and realized the effective dimensionality reduction of the data. Meanwhile, we adopted the logistic equation to accurately estimate the relevant parameters. Through the comprehensive analysis of eigenroot and variance contribution ratio, this paper successfully identifies the key factors, realizes the effective dimensionality reduction of the data, and adopts the logistic equation to accurately estimate the relevant parameters. The analysis results show that in the senior intelligent sports service index system, the highest weight value of platform is the operation and management platform, which reaches 0.4754. In the aspect of the demand for sports information of the seniors, the demand for online sports knowledge and skills is the highest, and the demand for online sports knowledge and skills is the highest. Regarding the demand for sports information of the elderly, the online acquisition of sports knowledge and skills has the highest demand of 203, followed by the demand for regular online sports knowledge lectures of 181. In the demand for outdoor bright trails, the elderly strongly want to enter their fitness and energy consumption data for evaluation, with a high degree of demand of 351. In addition, the demand for heart rate testing of the intelligent body testing station is the highest, with a degree of 186, followed by body fat testing, with a degree of 179. The Research in this paper not only focuses on the current situation and problems of intelligent sports services for the elderly, but also explores the methods and strategies to solve these problems, aiming to provide practical reference and guidance for the effective implementation of intelligent sports services for the elderly.

Learning Accurate Label-Specific Features From Partially Multilabeled Data.

Feature selection is an effective dimensionality reduction technique, which can speed up an algorithm and improve model performance such as predictive accuracy and result comprehensibility. The study of selecting label-specific features for each class label has attracted considerable attention since each class label might be determined by some inherent characteristics, where precise label information is required to guide label-specific feature selection. However, obtaining noise-free labels is quite difficult and impractical. In reality, each instance is often annotated by a candidate label set that comprises multiple ground-truth labels and other false-positive labels, termed partial multilabel (PML) learning scenario. Here, false-positive labels concealed in a candidate label set might induce the selection of false label-specific features while masking the intrinsic label correlations, which misleads the selection of relevant features and compromises the selection performance. To address this issue, a novel two-stage partial multilabel feature selection (PMLFS) approach is proposed, which elicits credible labels to guide accurate label-specific feature selection. First, the label confidence matrix is learned to help elicit ground-truth labels from the candidate label set via the label structure reconstruction strategy, each element of which indicates how likely a class label is ground truth. After that, based on distilled credible labels, a joint selection model, including label-specific feature learner and common feature learner, is designed to learn accurate label-specific features to each class label and common features for all class labels. Besides, label correlations are fused into the features selection process to facilitate the generation of an optimal feature subset. Extensive experimental results clearly validate the superiority of the proposed approach.