Search

Band selection is one of the most effective methods to reduce the band redundancy of hyperspectral images (HSIs). Most existing band selection methods tend to regard each band as a whole, and then explore the band redundancy with the pixel-wise features directly. However, since the regions of HSIs corresponding to different objects have diverse spectral properties and spatial structure, such above scheme limits the performance of hyperspectral band selection due to the lack of spatial information. To address above issues, a novel band selection method via region-aware latent features fusion based clustering (RLFFC) is proposed. Specifically, we employ the superpixel segmentation to segment HSIs into multiple regions so that the spatial information of HSIs can be fully preserved. In order to capture the priori information, we construct its corresponding Laplacian matrix from which a group of low dimensional latent features are generated to further enhance the separability among different bands. Then, a shared latent feature representation of HSIs is obtained by fusing region-aware latent features to effectively capture the band redundancy of HSIs. Finally, the k -means clustering algorithm is utilized to obtain the index of the selected bands from the shared latent feature representation. As a result, the spectral and spatial properties are well exploited in the proposed method. Extensive experiments on four public hyperspectral datasets show that the proposed method achieves superior performance when compared with other state-of-the-art ones.

A novel approach is proposed in this study for degrading aqueous glyphosate (GLYP) efficiently via electro-oxidation (EO) using a novel copper phthalocyanine (CuPc)-dispersed activated carbon fiber (ACF) electrode. Green synthesis of the CuPc-ACF electrode was achieved by electro-sorption process through oxidation-reduction of the Cu species, using cyclic voltammetry, also for the first time. The prepared electrode was directly applied to degrade the aqueous recalcitrant pollutant without supplementation of an electrolyte and external source of oxidant. Operating parameters of the EO system were optimized via response surface methodology (RSM) based on central composite design using performance index of the area under the curve (AUC). A complete degradation of a synthetic GLYP solution at high concentration (1000 mg L−1) was indicated at the optimized pH and biased potential of 11 and 2.5 V (vs Ag/AgCl), respectively. Kinetic assessment of the experimental data revealed a threshold voltage between 1.5 and 2.0 V required to trigger an effective and irreversible degradation of the aminomethyl phosphonic acid (AMPA) intermediate. The kinetics for degradation of GLYP was proposed via two pathways: a consecutive first-order reversible or an irreversible reaction forming the AMPA intermediate and a parallel reaction forming final transformed products. The study indicated a green route for the synthesis of the CuPc-ACF electrode for complete degradation of GLYP using EO as a green technology.

No-reference stereoscopic image quality assessment (NR SIQA) has aroused much attention in the multimedia application, but most current works cannot achieve reliable accuracy due to the non-visual meaning image patches and the weak biological visual models. Inspired by this, we propose a novel NR SIQA model by the introduction of the meaningful superpixel visual patches and the significant binocular perception models. Following the visual perceptual posterior probability theory, local monocular superpixel spatial entropy and the natural scene statistics (NSS) features are firstly utilized to present the high level semantic perceptual mechanism and image naturalness. Then the binocular biological models are applied to extract the binocular features to simulate the inner binocular interaction information, which well complement with the monocular features. Finally, a support vector regression (SVR) model is utilized to predict the objective quality score. Experiments are conducted on four popular stereoscopic image Databases, and the results demonstrate that the proposed model obtains a good consistency with the subjective scores, and has more reliable performance than previous works in terms of prediction accuracy and generalization capability.

The study investigated the synergistic effects of rGO and Pt over TiO2 for the HER via artificial photosynthesis under UVB and visible light irradiation. The introduction of glycerol and industrial wastewater to the system as sacrificial reductants signifies that the major reaction pathway is photocatalytic partial water splitting. The material characterizations revealed successful heterojunction formation and provided insight into chemistry behind the activity of the photocatalysts. Amongst various combinations of rGO on TiO2, 1GNT exhibited an HER yield five times that of bare TiO2 under UVB light. Addition of Pt led to the formation of a strong Schottky barrier at the heterojunction and consequently boosted HER performance. 1P0.5 GT presented the highest of 28.5 mmol g−1 h−1 with glycerol and 9.6 mmol g−1 h−1 with wastewater under UVB light respectively. For both binary and ternary photocatalysts, the HER performances dwindled under visible light irradiation, accentuating the insufficient activation of the TiO2. In addition, 1PT outperformed all the other photocatalysts thereby elucidating the impression that rGO and Pt does not work well together in enhancing HER despite quenching the exciton recombination rate of TiO2 significantly. The role of pH in the synthesis and the experiments has been discussed. Finally, the underlying mechanisms in the photodeposition and photoreformation have been proposed.

In this paper, we propose a novel shape-optimizing mesh warping method for stereoscopic panorama stitching, which aims to resolve shape distortion and unnatural rotation of traditional stitching methods, simultaneously coping with the challenges, misalignment , and stereoscopic inconsistency. Specifically, based on the grid mesh analysis of projective warping, we propose a differential warping method by gradually changing the inclination angle of each mesh line in non-overlapping regions of the image to reduce shape distortion and unnatural rotation. Furthermore, an extended moving direct linear transformation method is proposed to effectively and robustly improve alignment accuracy and maintain stereoscopic consistency in multiple stereoscopic images. Finally, a consistent seam based on the matched feature points in the left- and right- view images of a stereoscopic image is designed to blend images and generate a stereoscopic panorama image. Experiments demonstrate that the proposed method has a superior performance compared to previous methods.

Due to the rapid development of multimedia technology, a large number of unlabelled data with high dimensionality need to be processed. The high dimensionality of data not only increases the computation burden of computer hardware, but also hinders algorithms to obtain optimal performance. Unsupervised feature selection, which is regarded as a means of dimensionality reduction, has been widely recognized as an important and challenging pre-step for many machine learning and data mining tasks. However, we observe that there are at least two issues in previous unsupervised feature selection methods. Firstly, traditional unsupervised feature selection algorithms usually assume that the data instances are identically distributed and there is no dependency between them. However, the data instances are not only associated with high dimensional features but also inherently interconnected with each other. Secondly, the traditional similarity graph used in previous methods can only describe the pair-wise relations of data, but cannot capture the high-order relations, so that the complex structures implied in the data cannot be sufficiently exploited. In this work, we propose a robust unsupervised feature selection method which embeds the latent representation learning into feature selection. Instead of measuring the feature importances in original data space, the feature selection is carried out in the learned latent representation space which is more robust to noises. In order to capture the local manifold geometrical structure of original data in a high-order manner, a hypergraph is adaptively learned and embedded into the resultant model. An efficient alternating algorithm is developed to optimize the problem. Experimental results on eight benchmark data sets demonstrate the effectiveness of the proposed method.

This study is the first to use a newly-developed material via hydrothermal method, cerium oxide nanowires doped with reduced graphene oxide (CNW-RGO) for reductive H2 production. The detailed characteristics of the CNW-RGO materials were investigated to explore the capabilities of reductive production. The mean diameter of the CNWs was uniform at 22 nm. Owing to RGO-doping, the energy gap between the valence and conduction bands tended to become narrower that demonstrated by the density functional theory calculation (DFT). Furthermore, the optimum hydrogen production was 7.14 mmol g−1 by the CNW-RGO with a RGO content of 4 wt.% under the visible-light irradiation. This result was consistent with the turnover frequency (TOF) predictions. The introduction of RGO sheets effectively mediated the transfer of photogenerated electrons from the CNW to the sheets. Therefore, it could act as an electron trap to stimulate charge separation, which was corroborated by X-ray photoelectron spectroscopy (XPS) analysis. As indicated by comparative assessment, methanol was the most promising sacrificial agent in the system. Additionally, the formation of the methoxy group after the reaction was clearly demonstrated by Fourier-transform infrared (FTIR) spectroscopy. The number of hydroxyl groups on the alcohols directly determined their activity in reductive production.

Development of excellent sensors to determine trace concentrations of rifampicin is of intense importance for medicine analysis and human health. Herein, a facile and green fluorescent probe was established for the determination of rifampicin by using folic acid protected copper nanoclusters (FA-Cu NCs). Many characterization methods were applied for the analysis of the as-prepared FA-Cu NCs including UV-visible absorption spectra, fluorescence spectra, Fourier-transform infrared spectroscopy (FT-IR), transmission electron microscope (TEM), fluorescence lifetime and X-ray photoelectron spectroscopy (XPS). The TEM image suggested that the as-prepared FA-Cu NCs were highly dispersed. The as-synthesized FA-Cu NCs emerged blue fluorescence under UV light and demonstrated maximum emission wavelength at 446 nm under the maximum excitation wavelength of 358 nm. After the addition of rifampicin, the FL intensities of FA-Cu NCs were uncommonly quenched. The related experimental data intimated that the quenching mechanisms were assumed to the inner filter effect (IFE) and static quenching. The as-proposed probe platform displayed an obvious linear relationship with rifampicin concentrations varying from 0.5 to 100 µM, and the corresponding detection limit (LOD) was 0.073 µM (S/N = 3). Finally, the as-established detection platform was successfully employed to analyze trace concentrations of rifampicin in real samples.

Multi-view clustering aims to group data points into their classes. Exploiting the complementary information underlying multiple views to benefit the clustering performance is one of the topics of multi-view clustering. Most of existing multi-view clustering methods only constrain diversity and consistency in the data space, but not consider the diversity and consistency in the learned label space. However, It is natural to take the impacts of diversity in the learned label matrix into consideration, because different view would generate different clustering label matrix, in which some labels are consistent and some are diverse. To overcome this issue, we propose a novel multi-view clustering method (DCMSC) by constraining diversity and consistency in both the learned clustering label matrix and data space. Specifically, in the learned label space, we relax the learned common label matrix into consistent part and diverse part. Meanwhile, by applying an introduced row-aware diversity representation and l2,1-norm to constrain diverse part, wrong-labels and the influences of noises on the consistent part are reduced. In the data space, we weight each view by using a self-weight strategy. Furthermore, we conduct clustering in spectral embedded spaces instead of original data spaces, which suppresses the effect of noises and decreases redundant information. An augmented Lagrangian multiplier with alternating direction minimization (ALM-ADM) based optimization solution can guarantee the convergence of our method. Extensive experimental results on both synthetic datasets and real-world datasets demonstrate the effectiveness of our method.

Graphene is a one-atom-thick sheet, possessing a high electron mobility, constructed from sp2-bonded carbon atoms. Here, we hypothesize that graphene functions as a conductive material to promote anaerobic ammonium oxidation coupled with Fe(III) reduction (Feammox) in mangrove sediments slurries. In this study, graphene and 9,10-anthraquinone-2-sulfonate (AQS) were both investigated using a nitrogen isotope tracing technique. Graphene and AQS addition increased the Feammox rates by 31% and 56%. Graphene also increased the Fe(III) reduction rate by 43%, but Feammox-associated Fe(III) reduction accounted for only 1.5–4.9% of the total Fe(III) reduction. Graphene may have behaved as a conductive bridge to promote electron transfer to the Fe(III) acceptor in the Feammox process; however, the mechanisms by which graphene and AQS stimulate Feammox are different.

Prior studies mentioned that extracts of polyphenolics-abundant edible flora might provide compositions of reversible electron shuttles for bioenergy extraction; however, detailed mysteries behind such phenomena still remained open to be explored. This first-attempt study selected a medicinal herb Scutellaria baicalensis Georgi and its main flavonoid ingredients to quantitatively decipher their electron-mediating activities for bioenergy applications. The main ingredients with strong shuttling activities (e.g., baicalin, baicalein and wogonin) were chemical structure-associated to disclose electrochemical and bioenergetics characteristics for comparative analysis. Evidently, baicalin owned the most promising electron shuttling capabilities. Although extract of flavonoids-rich S. baicalensis Georgi also showed promising redox-mediating characteristics, typical ingredient-baicalein still exhibited high biotoxicity to bacterial CO2 respirometric production, thereby resisting fully expression of electron transfer capabilities. Supplementation of baicalin and extract of S. baicalensis Georgi to microbial fuel cells (MFCs) was conducted to quantify such stimulating capabilities of bioelectricity generation. That is, with toxicity attenuation, processed flavonoids-rich medicinal herbs were possibly electroactive for bioenergy extraction due to favorable electron-shuttling activities.

As one of the dimensionality reduction methods, unsupervised feature selection aims to select a subset of original features without the labels of data instances. It becomes more and more important since large amounts of unlabelled high dimensional data need to be processed in many machine learning and data mining tasks. In this paper, we propose a novel unsupervised feature selection method via compact feature representation, with the local geometrical structure of data being preserved by using a dual Laplacian graph regularization term. In detail, different to many previous representation based methods which use the original data as representation dictionary, we propose to learn a feature dictionary subspace for compact and robust feature representation. During the dictionary learning process, the l2,1-norm is imposed on the combination coefficient matrix to select discriminate features for constructing the latent feature dictionary. Meanwhile, the local geometrical structure of original data is preserved from the perspectives of subspace learning and feature representation. In general, our method conducts dictionary learning and unsupervised feature selection simultaneously. We develop an efficient optimization algorithm based on Alternating Direction Method of Multipliers to solve the proposed optimization problem and experiments on various types of real world datasets are conducted to demonstrate the effectiveness of the proposed method.

Upper limb tremor is common in people with multiple sclerosis (pwMS) and can affect day to day function, impacting on their tremor related quality of life (tremor-QOL). The Quality of Life in Essential Tremor Questionnaire (QUEST) is a tremor-QOL scale, however it has not been validated for use in pwMS. This is in contrast to the Multiple Sclerosis Impact Scale (MSIS-29), a MS health related QOL (MS-QOL) scale validated in pwMS. The aim of this study was to quantify tremor-QOL in pwMS using both the QUEST and MSIS-29 and establish the convergent validity of the QUEST scale with the MSIS-29.Data were derived from an existing registered clinical trial studying the efficacy of Botox (onabotulinumtoxinA) compared to placebo in pwMS-related upper limb tremor (ACTRN12617000379314). We determined MS-related disability (Expanded Disability status scale score (EDSS)), tremor severity (Bain and Findley Clinical Tremor Rating Scale (Bain)), cerebellar function (Scale for the Assessment and rating of Ataxia (SARA)), and upper limb manual dexterity (9 Hole Peg Test (9-HPT)). The QUEST and MSIS-29 were used to quantify tremor-QOL and MS-QOL respectively. Convergent validity was investigated by examining the correlation between QUEST and MSIS-29, and the pattern of correlation of the two scales compared to the EDSS, SARA, BAIN and 9-HPT.Our cohort of 57 patients (16 male; 41 female), mean age of 47.6, had moderate MS-related disability with median EDSS score of 5 (IQR = 3.5). Median Bain score was 8, indicating mild tremor severity, which corresponded to mild to moderately poor tremor-QOL given mean Quest Summary Index (QSI) of 45.7. QSI correlated to tremor severity as measured by Bain total score (rs(55) = 0.339, p 0.01), manual dexterity as measured by 9-HPT (rs(55) = 0.304, p 0.05), and MS disease activity measured by EDSS (rs(55) = 0.347, p 0.01). MSIS-29 also showed correlations to EDSS, and 9-HPT, but did not correlate to Bain total score. There was a strong relationship between QSI and MSIS-29 in pwMS (r(55) = 0.709, p 0.01).In this cross-sectional study, we found that both the MS-QOL and tremor-QOL of pwMS with upper limb tremor was reduced. We were also the first to demonstrate that tremor-QOL in pwMS with upper limb tremor can be measured using the QUEST, which may be better suited for use in pwMS affected by arm-tremor than the MSIS-29. There is a lack of literature to specifically address tremor-QOL in pwMS, and more research is warranted.

Multi-view unsupervised feature selection has been proven to be an effective approach to reduce the dimensionality of multi-view data. One of its key issues is how to exploit the underlying common structures across different views. In this paper, we propose a consensus learning guided multi-view unsupervised feature selection method, which embeds multi-view feature selection into a non-negative matrix factorization based clustering with sparse constrain. The proposed method learns latent feature matrices from all the views, and optimizes a consensus matrix such that the difference between the cluster indicator matrix of each view and the consensus matrix is minimized. The parameters for balancing the weights of different views are automatically adjusted, and a sparse constraint is imposed on the latent feature matrices to perform feature selection. After that, we design an effective iterative algorithm to solve the resultant optimization problem. Extensive experiments have been conducted on six publicly multi-view datasets, and the results demonstrate that the proposed algorithm outperforms several other state-of-the-art single view and multi-view unsupervised feature selection methods in terms of clustering tasks, validating the effectiveness of the proposed multi-view unsupervised feature selection method. The source code of our algorithm will be available on our on-line page: http://tangchang.net/ .

MNP-GO-TNT (Magnetic Nano Particle- Graphite Oxides- Titanium Nano Tubes) was synthesized with hydrothermal method. As(III) adsorption in solution was investigated. Lastly, the mechanisms of As(III) adsorption by MNP-GO-TNT at different pH was deciphered with FTIR and XPS. Besides, the infect factor for As(III) removal such as pH, initial concentration and temperature, etc. were discussed. At the same time, kinetic analysis and thermodynamic analysis has been analyzed. As(III) adsorption are benefit under acidic environment with higher temperature. As(III) adsorption with MNP-GO-TNT was followed in monolayer on surface of MNP-GO-TNT obtained from kinetic analysis. Furthermore, it a spontaneous reaction and endothermic reaction. In addition, the Ti–OH and Fe–OH groups of adsorbent are reacted during adsorption, and OH− is replaced by As(III). Therefore, the main reaction in this adsorption mechanism is chemical adsorption.

Graph-based saliency detection approaches have gained great popularity due to the simplicity and efficiency of graph algorithms. In these approaches, the saliency values of image elements are ranked by the similarity of image elements with foreground or background cues via graph-based ranking. However, in previous methods, the similarity between any two image elements on the affinity graph is computed by manually set functions which are sensitive to function parameters, and the constructed graph may not reveal the essentially relevance between feature vectors extracted from different image elements. In addition, during the saliency ranking process, all the initial labels contribute equally to the ranking function while the global saliency confidence of each image element is not taken into consideration. In order to address these two issues, we propose a bottom-up saliency detection approach by affinity graph learning and weighted manifold ranking. An unsupervised learning approach is introduced to learn the affinity graph based on image data self-representation. By setting image boundary superpixels as background seeds, the global saliency confidence prior implied in the affinity matrix is utilized to weight the saliency ranking. In such a manner, the superpixels with higher saliency confidences will be assigned higher saliency values in the final saliency map and the background superpixels can be efficiently suppressed. Comprehensive evaluations on three challenge datasets indicate that our algorithm universally surpasses other unsupervised graph based saliency detection methods.

Different from traditional action recognition based on video segments, online action recognition aims to recognize actions from an unsegmented stream of data in a continuous manner. One approach to online recognition is based on accumulation of evidence over time. This paper presents an effective framework of such an approach to online action recognition from a stream of noisy skeleton data, using a weighted covariance descriptor as a means to accumulate information. In particular, a fast incremental updating method for the weighted covariance descriptor is developed. The weighted covariance descriptor takes the following principles into consideration: past frames have less contribution to the accumulated evidence and recent and informative frames such as key frames contribute more. To determine the discriminativeness of each frame, an effective pseudo-neutral pose is proposed to recover the neutral pose from an arbitrary pose in a frame. Two recognition methods are developed using the weighted covariance descriptor. The first method applies nearest neighbor search in a set of trained actions using a Riemannian metric of covariance matrices. The second method uses a Log-Euclidean kernel based SVM. Extensive experiments on MSRC-12 Kinect Gesture dataset, Online RGBD Action dataset, and our newly collected online action recognition dataset have demonstrated the efficacy of the proposed framework in terms of latency, miss rate and error rate.

This first-attempt study revealed optimal strategy to supplement extracts of polyphenolics-abundant medicinal herbs and Camellia tea as electron shuttles (ESs) for stimulating bioenergy generation in microbial fuel cells (MFCs). Apparently, Camellia sinensis (L.) Kuntze and Syzygium aromaticum were promising electroactive ESs. Moderate temperature (ca. 65 °C) and slightly alkali pHs (∼10) were electrochemically feasible conditions for herbal extraction. Optimal contents of polyphenolics-rich herbs and tea extracts with maximal electrochemical activities could be stably obtained. Power density of MFC supplemented with Camellia green tea extract could significantly increase ca. 176%, suggesting that green tea extract would be the most appropriate ESs. Total phenolic contents and electron shuttling capabilities were all electrochemically associated. In addition, chemical structure strongly affected whether antioxidant activities of polyphenolics-abundant herbal extracts could be reversibly switched to be electron-shuttling capabilities (e.g., substitution patterns). Hydroxyl substiutuents ortho or para to each other were very likely promising for electron-shuttling, but not for meta substituents. Moreover, bioelectrochemical treatment upon medicinal herbal extracts (e.g., cyclic electron-donating and withdrawing processes) might be inevitably needed for toxicity attenuation to fully express bioenergy-shuttling activities.

The present paper reports on an evaluation of Batvox 3.1 as part of the Speech Communication virtual special issue: Multi-laboratory evaluation of forensic voice comparison systems under conditions reflecting those of a real forensic case (forensic_eval_01). We were interested in the effect of the amount of training data on the performance of the system. We therefore tested Batvox 3.1 using different sized sets of data randomly selected from the forensic_eval_01 training data: one known-speaker-condition recording and one questioned-speaker-condition recording from each of 25, 50, 75, and 100 speakers. The results show that the performance of the system continued to improve as the amount of training data increased. Previously reported results for Batvox 4.1 (an i-vector PLDA system) were better than those for Batvox 3.1 (a GMM-UBM system).

Recent research indicates the critical importance of preserving local geometric structure of data in unsupervised feature selection (UFS), and the well studied graph Laplacian is usually deployed to capture this property. By using a squared l2-norm, we observe that conventional graph Laplacian is sensitive to noisy data, leading to unsatisfying data processing performance. To address this issue, we propose a unified UFS framework via feature self-representation and robust graph regularization, with the aim at reducing the sensitivity to outliers from the following two aspects: i) an l2, 1-norm is used to characterize the feature representation residual matrix; and ii) an l1-norm based graph Laplacian regularization term is adopted to preserve the local geometric structure of data. By this way, the proposed framework is able to reduce the effect of noisy data on feature selection. Furthermore, the proposed l1-norm based graph Laplacian is readily extendible, which can be easily integrated into other UFS methods and machine learning tasks with local geometrical structure of data being preserved. As demonstrated on ten challenging benchmark data sets, our algorithm significantly and consistently outperforms state-of-the-art UFS methods in the literature, suggesting the effectiveness of the proposed UFS framework.

Unsupervised feature selection has become an important and challenging pre-processing step in machine learning and data mining since large amount of unlabelled high dimensional data are often required to be processed. In this paper, we propose an efficient method for robust unsupervised feature selection via dual self-representation and manifold regularization, referred to as DSRMR briefly. On the one hand, a feature self-representation term is used to learn the feature representation coefficient matrix to measure the importance of different feature dimensions. On the other hand, a sample self-representation term is used to automatically learn the sample similarity graph to preserve the local geometrical structure of data which has been verified critical in unsupervised feature selection. By using l2,1-norm to regularize the feature representation residual matrix and representation coefficient matrix, our method is robustness to outliers, and the row sparsity of the feature coefficient matrix induced by l2,1-norm can effectively select representative features. During the optimization process, the feature coefficient matrix and sample similarity graph constrain each other to obtain optimal solution. Experimental results on ten real-world data sets demonstrate that the proposed method can effectively identify important features, outperforming many state-of-the-art unsupervised feature selection methods in terms of clustering accuracy (ACC) and normalized mutual information (NMI).