Search

Simple Summary: Identifying silkworm pupae species and sex accurately is essential for the hybrid pairing of corresponding species in sericulture, which guarantees the quality of the silkworm eggs and silk. However, there is no cost-effective method that offers a labor-saving and intelligent solution for this. In this study, machine learning and deep learning are used for the automatic recognition of pupae species and sex, either separately or simultaneously, based on the patterns perceived from images. A vast number of postural images of pupae were used for global modeling to eliminate the impact of posture on recognition rate. Six traditional descriptors and six deep learning descriptors were employed for feature extraction and then combined with three machine learning classifiers for identification. Based on that, the model with the best identification performance was screened out, and it can serve as a reference for sericulture breeding. Hybrid pairing of the corresponding silkworm species is a pivotal link in sericulture, ensuring egg quality and directly influencing silk quantity and quality. Considering the potential of image recognition and the impact of varying pupal postures, this study used machine learning and deep learning for global modeling to identify pupae species and sex separately or simultaneously. The performance of traditional feature-based approaches, deep learning feature-based approaches, and their fusion approaches were compared. First, 3600 images of the back, abdomen, and side postures of 5 species of male and female pupae were captured. Next, six traditional descriptors, including the histogram of oriented gradients (HOG), and six deep learning descriptors, including ConvNeXt-S, were utilized to extract significant species and sex features. Finally, classification models were constructed using the multilayer perceptron (MLP), support vector machine, and random forest. The results indicate that the {HOG + ConvNeXt-S + MLP} model excelled, achieving 99.09% accuracy for separate species and sex recognition and 98.40% for simultaneous recognition, with precision–recall and receiver operating characteristic curves ranging from 0.984 to 1.0 and 0.996 to 1.0, respectively. In conclusion, it can capture subtle distinctions between pupal species and sexes and shows promise for extensive application in sericulture. [ABSTRACT FROM AUTHOR]

Simple Summary: The widespread cultivation of genetically engineered crops producing not only toxic proteins from the bacterium Bacillus thringiensis (Bt) but also plant defensive compounds known as allelochemicals, combined with occasional use of insecticides, is the major tactic to manage some economically important pests. Better understanding of the toxicological interactions of the three types of toxins is needed to rationally deploy them to protect crops from pests. The aim of this study is to examine the sequential and simultaneous interactions of the allelochemical flavone, Bt toxin Vip3A, and insecticide emamectin benzoate in the fall armyworm (Spodoptera frugiperda), a worldwide target pest of Bt crops. Bioassays of S. frugiperda neonates revealed that all interactions of the three toxins, except for 1-day pre-exposure to a sublethal dose (LC5) of flavone followed by 6-day simultaneous exposure to flavone LC5 + emamectin benzoate LC50, are synergistic or additive. The results suggest that the combined use of the three toxins is basically a great strategy to manage S. frugiperda. Target pests of genetically engineered crops producing both defensive allelochemicals and Bacillus thuringiensis (Bt) toxins often sequentially or simultaneously uptake allelochemicals, Bt toxins, and/or insecticides. How the three types of toxins interact to kill pests remains underexplored. Here we investigated the interactions of Bt toxin Vip3A, plant allelochemical flavone, and insecticide emamectin benzoate in Spodoptera frugiperda. Simultaneous administration of flavone LC25 + Vip3A LC25, emamectin benzoate LC25 + Vip3A LC25, and flavone LC15 + emamectin benzoate LC15 + Vip3A LC15 but not flavone LC25 + emamectin LC25 yielded a mortality significantly higher than their expected additive mortality (EAM). One-day pre-exposure to one toxin at LC5 followed by six-day exposure to the same toxin at LC5 plus another toxin at LC50 showed that the mortality of flavone LC5 + Vip3A LC50, emamectin benzoate LC5 + Vip3A LC50, and Vip3A LC5 + emamectin benzoate LC50 were significantly higher than their EAM, while that of flavone LC5 + emamectin benzoate LC50 was significantly lower than their EAM. No significant difference existed among the mortalities of Vip3A LC5 + flavone LC50, emamectin benzoate LC5 + flavone LC50, and their EAMs. The results suggest that the interactions of the three toxins are largely synergistic (inductive) or additive, depending on their combinations and doses. [ABSTRACT FROM AUTHOR]

Purpose. We performed a genome-wide analysis of long noncoding RNA (lncRNA) expression to identify novel targets for the further study of recombinant human erythropoietin (rhEPO) treatment of acute spinal cord injury (SCI) in rats. Methods. Nine rats were randomly divided into 3 groups. No operation was performed in group 1. In groups 2 and 3, a laminectomy was performed at the 10th thoracic vertebra, and a contusion injury was induced by extradural application of an aneurysm clip. Group 1 rats did not receive any treatment, group 2 rats received a single intraperitoneal injection of normal saline, and group 3 rats received rhEPO. Three days after injury, spinal cord tissues were collected for RNA-Seq, microarray, differentially expressed genes (DEGs), Gene Ontology (GO) function enrichment, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment, and protein-protein interaction (PPI) analyses. Results. Compared with group 1, 4,446 genes were found to be differentially expressed in group 2. Furthermore, 99 lncRNAs were found to be changed in the injury group. The data indicate that 2,471 mRNAs were upregulated, and 1,975 mRNAs were downregulated in group 2 as compared with group 1. In addition, 45 of the lncRNAs were upregulated, and the other 44 lncRNAs were downregulated. The top 5 upregulated and top 5 downregulated lncRNAs that were different between group 2 and group 1 are shown. The top 5 downregulated and the top 5 upregulated lncRNAs that were different between group 3 and group 2 are shown. Conclusion. RhEPO treatment alters the expression profiles of the differentially expressed lncRNAs and genes beneficial to the development of new treatments. [ABSTRACT FROM AUTHOR]

For graph-based multi-view clustering, a critical issue is to capture consensus cluster structures via a two-stage learning scheme. Specifically, first learn similarity graph matrices of multiple views and then fuse them into a unified superior graph matrix. Most current methods learn pairwise similarities between data points for each view independently, which is widely used in single view. However, the consensus information contained in multiple views are ignored, and the involved biases lead to an undesirable unified graph matrix. To this end, we propose a bipartite graph based multi-view clustering (BIGMC) approach. The consensus information can be represented by a small number of representative uniform anchor points for different views. A bipartite graph is constructed between data points and the anchor points. BIGMC constructs the bipartite graph matrices of all views and fuses them to produce a unified bipartite graph matrix. The unified bipartite graph matrix in turn improves the bipartite graph similarity matrix of each view and updates the anchor points. The final unified graph matrix forms the final clusters directly. In BIGMC, an adaptive weight is added for each view to avoid outlier views. A low-rank constraint is imposed on the Laplacian matrix of the unified matrix to construct a multi-component unified bipartite graph, where the component number corresponds to the required cluster number. The objective function is optimized in an alternating optimization fashion. Experimental results on synthetic and real-world data sets demonstrate its effectiveness and superiority compared with the state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

A silver nanoparticles (AgNPs) catalyzed clock reaction of 4‐nitrophenol (4‐NP) and NaBH4 was fabricated for multi‐mode detection of tetracyclines (TCs). The yellow 4‐NP was reduced to the colorless 4‐aminophenol (4‐AP) using AgNPs as the nanocatalysts, however, it took relatively longer time in the presence of TCs because the AgNPs' catalytic surface was capped by TCs. The catalytic activity of AgNPs with different concentrations of TCs could be reflected by the visual color and the reaction time of the 4‐NP‐NaBH4 system, which was quantatively measured through chronometric and colorimetric responses. Under the optimal conditions, the detection limits of four TCs were 6.7 to 14.3 nM with the chronometric assay and 28.5 to 42.3 nM with colorimetric assay, respectively. The proposed methods were sensitive to monitor multiple TCs in an economical way, which was successfully applied for detecting of TCs in various environmental water samples. [ABSTRACT FROM AUTHOR]

Herein, a dual-emission Eu metal-organic framework (Eu-MOF) is prepared and used as the ratiometric fluorescence probe for ultrasensitive detection of aminoglycoside antibiotics (AGs). Due to the strong hydrogen bond interactions between AGs and Eu-MOF, the blue emission is enhanced while the red emission has little fluctuation in Eu-MOF with the addition of AGs, thus a good linear relationship with the logarithm of AGs concentrations from 0.001 to 100 μg/mL can be established for quantitative analysis. Good sensitivity with the detection limit of 0.33 ng/mL for apramycin, 0.32 ng/mL for amikacin and 0.30 ng/mL for kanamycin is achieved. The proposed assay demonstrates good selectivity and applicability for determination of AGs in real milk and honey samples. The Eu-MOF materials are further fabricated as fluorescent test papers for facile visual detection. The as-established ratio fluorescence platform offers a portable and economical way for rapid monitoring AGs residues in complex food samples. Synopsis: The Eu-MOF is composed of two ligands of 2-aminoterephthalic acid (BDC-NH 2) and 1,10-phenanthroline (phen) that coordinated to Eu3+, which emits blue fluorescence at 434 nm and red fluorescence at 613 nm under 365 nm excitation. In the presence of AGs, the blue emission is enhanced while the red emission has little fluctuation in Eu-MOF, thus detection of AGs is achieved by using Eu-MOF as ratiometric fluorescence probe, and the visual fluorescence variation from red to purple to blue can be readout by naked eyes using Eu-MOF loaded test paper. [Display omitted] • Eu-MOF ratiometric fluorescence probe is designed for ultrasenstive AGs detection. • Detection mechanism is based on enhancing the ICT effect of Eu-MOF by adding AGs. • Eu-MOF test paper is further fabricated as portable sensor for visual analyzing AGs. • It offers an economical way for rapid detection of AGs residues in real food samples. [ABSTRACT FROM AUTHOR]

Arsenic (As) has been widely detected in surface media on the Qinghai-Tibetan Plateau (QTP); however, the differences in the As distribution and partitioning characteristics between freshwater and saltwater lakes remain poorly understood. To determine the distribution and partitioning characteristics of As, multimedia environmental samples were collected from a typical small watershed consisting of a river, wetland, and both freshwater and saltwater lakes on the QTP. Results showed that freshwater systems, represented by Hurleg Lake, were high in particulate arsenic (PAs) and low in dissolved arsenic (DAs), whereas the saltwater system represented by Tosen Lake, exhibited the reverse distribution. This discrepancy in As distribution was primarily attributed to evaporation enrichment, competitive adsorption of HCO 3 − and pH variations, as suggested by correlation analysis and stable isotopic composition of water. In the stratified Tosen Lake, an increasing trend of DAs in the water column was observed, potentially driven by the reductive dissolution of Fe (hydr)oxides and bacterial sulfate reduction in the anoxic bottom hypolimnion. Conversely, Hurleg Lake maintained oxic conditions with stable DAs concentrations. Notably, PAs was elevated in the bottom layer of both lakes, possibly due to uptake/adsorption by biogenic particles, as indicated by high levels of chl.α and suspended particulate matter. These findings offer insights into the potential future impact of climate change on As mobilization/redistribution in arid plateau lakes, with implications for management policies that regulate As pollution. [Display omitted] • Freshwater exhibited elevated particulate As while saltwater was high in dissolved As. • High HCO 3 − and pH favored As release from suspended particulate matter in saltwater. • Uptake/adsorption by biogenic origin particulates was significant. • Lake expansion would enhance arsenic adsorption. [ABSTRACT FROM AUTHOR]

By using the terminal sliding-mode control (TSMC) and the pinning control methods, the fully distributed finite-time consensus problems are investigated for second-order multiagent systems (MASs) and multiquadcopter systems (MQSs) with directed topology. For the second-order MASs, a pinning control scheme is designed by analyzing the outdegree and indegree of nodes, and a TSMC protocol with the local information is proposed to achieve the finite-time consensus. Then, as an application of the MASs, the model of MQSs is constructed and its finite-time attitude consensus is discussed. Finally, the effectiveness of the proposed method is validated by two numerical examples. [ABSTRACT FROM AUTHOR]

This article investigates the privacy-preserving average consensus problem for the general continuous-time multiagent network systems (MANSs) with time delay via the event-triggered communication scheme. In order to avoid disclosing the initial states of the network agents and at the same time achieve the agents’ consensus for MANSs with time delay, a novel consensus control algorithm based on a new privacy-preserving approach is proposed. The new privacy-preserving approach is that we construct an output mask to make agents’ internal states indiscernible by others, which is different from the existing privacy-preserving methods adding random noises to the update law of agents’ states. Compared with the existing privacy-preserving methods, our approach makes all agents in MANSs exactly converge to the average value of initial states instead of its mean square value. Based on the proposed algorithm, we carry out the detailed theoretical consensus analysis of the network agents, from which, it is shown that the upper bound of the communication time delay between neighbors’ agents can be estimated approximately. Moreover, the Zeno-behavior of event-triggered time sequences for each agent is excluded. Finally, two simulation examples are performed to demonstrate the effectiveness of our theoretical results. [ABSTRACT FROM AUTHOR]

In this paper, an optimal risk-averse configuration framework for hybrid energy storage system (HESS) is proposed in planning utility-scale photovoltaic (PV) plants with conditional generative adversarial networks (CGANs)-based PV scenario generation. Other than most existing economy-based methods, we focus on frequency-based method to size a battery-supercapacitor HESS for mitigating the PV generation fluctuations in two time scales. We explore for the first time the potential of CGANs to generate sufficient PV scenarios through learning for experimental data preparation. For satisfying the fluctuation restrictions strictly, a data-driven frequency-based batteries optimization is developed, combining the flexible low-pass filter with wavelet package transform to guide the behaviors of both battery and supercapacitor for every individual scenario. Moreover, to hedge against risk exposure imposed by uncertain PV resource, we employ conditional value-at-risk to perform the optimal risk-averse configuration to meet the fluctuation mitigating requirements and minimize the expected configuration as well as the risk. Case studies are provided to verify the reasonableness and the efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

This paper studies quasi-synchronization in networked heterogeneous harmonic oscillators. By introducing a leader, two distributed synchronization protocols are first proposed for heterogeneous networks by utilizing continuous real-time information and aperiodic sampled-data information. Then, the sufficient conditions on quasi-synchronization are established for heterogeneous networks coupled with nonidentical harmonic oscillators. It is found that each follower oscillator can converge to a bounded region of the leader by adopting either a continuous-time protocol or sampled-data protocol. The upper bound of the region is solved for networked heterogeneous harmonic oscillators. Finally, an electrical network is provided to illustrate the applicability of the theoretical results, and two examples are provided to illustrate the effectiveness of the sufficient criteria. [ABSTRACT FROM AUTHOR]

In data mining, large differences between multi-class distributions regarded as class imbalance issues have been known to hinder the classification performance. Unfortunately, existing sampling methods have shown their deficiencies such as causing the problems of over-generation and over-lapping by oversampling techniques, or the excessive loss of significant information by undersampling techniques. This paper presents three proposed sampling approaches for imbalanced learning: the first one is the entropy-based oversampling (EOS) approach; the second one is the entropy-based undersampling (EUS) approach; the third one is the entropy-based hybrid sampling (EHS) approach combined by both oversampling and undersampling approaches. These three approaches are based on a new class imbalance metric, termed entropy-based imbalance degree (EID), considering the differences of information contents between classes instead of traditional imbalance-ratio. Specifically, to balance a data set after evaluating the information influence degree of each instance, EOS generates new instances around difficult-to-learn instances and only remains the informative ones. EUS removes easy-to-learn instances. While EHS can do both simultaneously. Finally, we use all the generated and remaining instances to train several classifiers. Extensive experiments over synthetic and real-world data sets demonstrate the effectiveness of our approaches. [ABSTRACT FROM AUTHOR]

In this paper, we develop a decentralized event-triggered control (ETC) strategy for a class of nonlinear systems with uncertain interconnections. To begin with, we show that the decentralized ETC policy for the whole system can be represented by a group of optimal ETC laws of auxiliary subsystems. Then, under the framework of adaptive critic learning, we construct the critic networks to solve the event-triggered Hamilton–Jacobi–Bellman equations related to these optimal ETC laws. The weight vectors used in the critic networks are updated by using the gradient descent approach and the experience replay (ER) technique together. With the aid of the ER technique, we can conquer the difficulty arising in the persistence of excitation condition. Meanwhile, by using classic Lyapunov approaches, we prove that the estimated weight vectors used in the critic networks are uniformly ultimately bounded. Moreover, we demonstrate that the obtained decentralized ETC can force the overall system to be asymptotically stable. Finally, we present an interconnected nonlinear plant to validate the proposed decentralized ETC scheme. [ABSTRACT FROM AUTHOR]

Inspired by biological mechanisms and structures in neuroscience, many biologically inspired visual computational models have been presented to provide new solutions for visual recognition task. For example, convolutional neural network (CNN) was proposed according to the hierarchical structure of biological vision, which could achieve superior performance in large-scale image classification. In this paper, we propose a new framework called visual interaction networks (VIN-Net), which is inspired by visual interaction mechanisms. More specifically, self-interaction, mutual-interaction, multi-interaction, and adaptive interaction are proposed in VIN-Net, forming the first interactive completeness of the visual interaction model. To further enhance the representation ability of visual features, the adaptive adjustment mechanism is integrated into the VIN-Net model. Finally, our model is evaluated on three benchmark datasets and two self-built textile defect datasets. The experimental results demonstrate that the proposed model exhibits its efficiency on visual classification tasks. Furthermore, a textile industrial application shows that the proposed architecture outperforms the state-of-the-art approaches in classification performance. [ABSTRACT FROM AUTHOR]

In this paper, we study the event-triggered robust stabilization problem of nonlinear systems subject to mismatched perturbations and input constraints. First, with the introduction of an infinite-horizon cost function for the auxiliary system, we transform the robust stabilization problem into a constrained optimal control problem. Then, we prove that the solution of the event-triggered Hamilton–Jacobi–Bellman (ETHJB) equation, which arises in the constrained optimal control problem, guarantees original system states to be uniformly ultimately bounded (UUB). To solve the ETHJB equation, we present a single network adaptive critic design (SN-ACD). The critic network used in the SN-ACD is tuned through the gradient descent method. By using Lyapunov method, we demonstrate that all the signals in the closed-loop auxiliary system are UUB. Finally, we provide two examples, including the pendulum system, to validate the proposed event-triggered control strategy. [ABSTRACT FROM AUTHOR]

This paper analyzes the consensus problem in heterogenous nonlinear multiagent systems. The multiagent systems not only have nonidentical nonlinear dynamics for all agents, but also have different network topologies for position and velocity interactions. An asynchronous sampled-data control without any input delays is first proposed, the information of each agent is only sampled at its own sampling instants and need not be sampled at other sampling instants. Then, quasi-consensus in heterogenous multiagent systems is proved by Lyapunov stability theory. When asynchronous sampled-data control has nonuniform input delays, sufficient conditions for quasi-consensus in heterogenous multiagent systems are further obtained. The upper bound of quasi-consensus errors is estimated. Finally, numerical simulations are provided to verify the effectiveness of theoretical results. [ABSTRACT FROM AUTHOR]

This paper presents a novel decentralized control strategy for a class of uncertain nonlinear large-scale systems with mismatched interconnections. First, it is shown that the decentralized controller for the overall system can be represented by an array of optimal control policies of auxiliary subsystems. Then, within the framework of adaptive dynamic programming, a simultaneous policy iteration (SPI) algorithm is developed to solve the Hamilton–Jacobi–Bellman equations associated with auxiliary subsystem optimal control policies. The convergence of the SPI algorithm is guaranteed by an equivalence relationship. To implement the present SPI algorithm, actor and critic neural networks are applied to approximate the optimal control policies and the optimal value functions, respectively. Meanwhile, both the least squares method and the Monte Carlo integration technique are employed to derive the unknown weight parameters. Furthermore, by using Lyapunov’s direct method, the overall system with the obtained decentralized controller is proved to be asymptotically stable. Finally, the effectiveness of the proposed decentralized control scheme is illustrated via simulations for nonlinear plants and unstable power systems. [ABSTRACT FROM AUTHOR]

This paper develops a new online learning consensus control scheme for multiagent discrete-time systems by goal representation heuristic dynamic programming (GrHDP) techniques. The agents in the whole system are interacted with each other through a communication graph structure. Therefore, each agent can only receive the information from itself and its neighbors. Our goal is to design the GrHDP method to achieve consensus control which makes all the agents track the desired dynamics and simultaneously makes the performance indices reach Nash equilibrium. The new local internal reinforcement signals and local performance indices are provided for each agent and the corresponding distributed control laws are designed. Then, GrHDP algorithm is developed to solve the multiagent consensus control problem with the proof of convergence. It is shown that the designed local internal reinforcement signals are bounded signals and the local performance indices can monotonically converge to their optimal values. Moreover, the desired distributed control laws can also achieve optimal. Two simulation studies, including one with four agents and another with ten agents, are applied to validate the theoretical analysis and also demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

• A new smooth distance-based class-wise statistic is introduced to measure the coherence of each class. • A variant of Extended Nearest Neighbor algorithm with metric learning is developed for classification. • The gradient of the loss function is derived and an iterative learning algorithm is developed. • Extensive experimental results with significance tests on real-life datasets demonstrates the effectiveness of the proposed approach. Recent studies have shown that extended nearest neighbor (ENN) method is able to improve the classification performance over traditional k -nearest neighbor (KNN) methods, due to its novel "two-way communication" decision making process. The ENN method classifies a test data sample by maximizing the intra-class coherence gain over the whole data set. However, the original ENN method, like KNN, is a type of instance-based learning algorithm without a training stage. This paper presents a variant of ENN method, called M aximum intra-class C oherence E xtended N earest N eighbor (MCENN), which incorporates distances between individual data sample and its nearest neighbors into the decision making process and introduces a novel distance metric learning algorithm as a training process to learn an optimal linear transformation that maximizes the overall intra-class coherence of training data. We demonstrate that the proposed MCENN approach is able to improve the discriminative performance for pattern recognition. Experimental results on real-life data sets demonstrate the effectiveness of the proposed approaches. [ABSTRACT FROM AUTHOR]

Reliability classification of gear safety has long been a challenging issue in transmission industry because of complicated calculations and great classification errors of coupled parameters with insufficient data. This paper proposes a model based on generative adversarial network (GAN) as pretreatment to improve the accuracy of reliability classification. First, we present bounded-GAN to generate gear data within required boundaries without massive computations. In bounded-GAN, three bounded layers are designed to bound generated data in terms of different data characteristics; smooth targets are developed to enhance the ability of generating high-quality instances by the generator; Adam optimizer is used to train both generator and discriminator to avoid nonconvergence. Second, to overcome unlabeling defect of bounded-GAN, a mean–covariance labeling scheme is introduced to label the data according to the nearest classes of gear reliability within specific ranges. Finally, original and qualified data are combined to train classifiers. Simulations on gear data from industry show that our proposed model outperforms other methods on operational metrics. [ABSTRACT FROM AUTHOR]

Biological carbon pumping (BCP) is a key process in which dissolved inorganic carbon in terrestrial aquatic ecosystems is utilized by aquatic autotrophs for photosynthesis and transformed into autochthonous organic matter (AOC). However, the mechanisms underlying BCP and the amount of generated AOC deposited effectively, are still poorly understood. Therefore, we conducted a systematic study combining modern hydrochemical monitoring and a sediment trap experiment in Fuxian Lake (Yunnan, SW China), the second-deepest plateau, oligotrophic freshwater lake in China. Temperature, pH, EC (electrical conductivity), DO (dissolved O2), [HCO3−], [Ca2+], SIc, partial CO2 (pCO2) pressure, and carbon isotopic compositions of HCO3− (δ13CDIC) in water from Fuxian Lake all displayed distinct seasonal and vertical variations. This was especially apparent in an inverse correlation between pCO2 and DO, indicating that variations of hydrochemistry in the lake water were mainly controlled by the metabolism of the aquatic phototrophs. Furthermore, the lowest C/N ratios and highest δ13Corg were recorded in the trap sediments. Analyses of the C/N ratio demonstrated that the proportions of AOC ranged from 30% to 100% of all OC, indicating that AOC was an important contributor to sedimentary organic matter (OC). It was calculated that the AOC flux in Fuxian Lake was 20.43 t C km−2 in 2017. Therefore, AOC produced by carbonate weathering and aquatic photosynthesis could potentially be a significant carbon sink and may have an important contribution to solving the lack of carbon sinks in the global carbon cycle. [ABSTRACT FROM AUTHOR]

In term of data-driven techniques for reliability assessment of transmission gears, it is necessary to collect sufficient data of each class in practice. However, the fact that highest and lowest reliability events rarely occur would result in a class imbalance problem. To resolve such an issue, we propose conditional generative adversarial network-mean-covariance balancing labeling (CGAN-MBL) to improve reliability assessment of transmission gears with insufficient and imbalanced data. First, we establish a CGAN-based model to generate credible instances with a similar distribution of original data. In the model, it is proven that by introducing a network weight initialization scheme, the ability to escape from local optimum is enhanced and global search ability of CGAN is strengthened; minibatch discriminator is designed to decrease mode collapse by distinguishing a batch of original and generated data iteratively. Second, in order to overcome the drawback of CGAN with unlabeled generated data, MBL is introduced to tag the generated data through exploring the nearest distance between generated instances and original class centers. Finally, synthetic data combined generated data with original ones train classifiers. Simulations show the effectiveness of the proposed approach for imbalance learning in real-world transmission gear data. [ABSTRACT FROM AUTHOR]

This paper develops an optimal control scheme for continuous-time unknown nonlinear systems using the event-triggering mechanism. Different from designing controllers using the time-triggering mechanism, the event-triggered controller is updated only when the system state deviates more than a certain threshold from a prescribed value. To obtain the event-triggered optimal controller, we develop an identifier-critic architecture under the framework of reinforcement learning. The identifier network, composed of a feedforward neural network (FNN), aims to derive the knowledge of unknown system dynamics, and the critic network, constituted of an FNN, intends to derive the event-triggered optimal controller. The identifier network is tuned via the combination of a standard back-propagation algorithm and an ${e}$ -modification method, and the critic network is updated using a modification of the gradient descent method. By introducing an additional stability term to update the critic network, the initial admissible control is no longer required. Meanwhile, by using historical and instantaneous state data together, the persistence of excitation condition is relaxed. A stability analysis of the closed-loop system is provided based on the Lyapunov method. The effectiveness of the proposed designs is illustrated through simulations of a nonlinear example and a single link robot arm system. [ABSTRACT FROM AUTHOR]

Synopsis: In the presence of SCN-, Fe2+ is added to the system, and Au NPLs are gradually etched, the triangular tip gradually becomes smooth during etching, and finally fully etched into spherical particles. The color of the solution gradually changes from blue to purple and finally to pink. [Display omitted] • Fenton-reaction stimulated etching of Au NPLs is constructed. • Colorimetric and visual sensing of Fe2+ is achieved through the etching of Au NPLs. • The proposed assay exhibits high sensitivity and selectivity towards Fe2+. • Facile monitoring of Fe2+ in environmental and biological samples is demonstrated. In this study, a method for ultrasensitive sensing of Fe2+ based on Fenton reaction mediated etching of triangular gold nanoplates (Au NPLs) was developed. In this assay, the etching of Au NPLs by H 2 O 2 was accelerated in the presence of Fe2+ due to the generation of superoxide free radical (O 2 ·-) via Fenton reaction. With the concentration of Fe2+ increased, the shape of Au NPLs changed from triangular to sphere with the blue shifted localized surface plasmon resonance, accompanying a series of consecutive color changes from blue, bluish purple, purple, reddish purple and finally to pink. The rich color variations enable rapid visual quantitative determination of Fe2+ within 10 min. A good linear relationship between the peak shifts and the concentration of Fe2+ was obtained in the range of 0.035 to 1.5 μM (R2 = 0.996). Favorable sensitivity and selectivity in the presence of other tested metal ions were achieved in the proposed colorimetric assay. The detection limits (3ơ/ k) for Fe2+ was 26 nM by UV–vis spectroscopy, and the clearly discernible concentration of Fe2+ was as low as 0.07 μM by naked eyes. The recoveries of fortified samples in pond water and serum samples ranged from 96% to 106% with interday relative standard deviations <3.6% in all cases, demonstrating the applicability of the assay for measuring Fe2+ in real samples. [ABSTRACT FROM AUTHOR]

This paper proposes a novel intelligent fault diagnosis method to automatically identify different health conditions of wind turbine (WT) gearbox. Unlike traditional approaches, where feature extraction and classification are separately designed and performed, this paper aims to automatically learn effective fault features directly from raw vibration signals while classify the type of faults in a single framework, thus providing an end-to-end learning-based fault diagnosis system for WT gearbox without additional signal processing and diagnostic expertise. Considering the multiscale characteristics inherent in vibration signals of a gearbox, a new multiscale convolutional neural network (MSCNN) architecture is proposed to perform multiscale feature extraction and classification simultaneously. The proposed MSCNN incorporates multiscale learning into the traditional CNN architecture, which has two merits: 1) high-level fault features can be effectively learned by the hierarchical learning structure with multiple pairs of convolutional and pooling layers; and 2) multiscale learning scheme can capture complementary and rich diagnosis information at different scales. This greatly improves the feature learning ability and enables better diagnosis performance. The proposed MSCNN approach is evaluated through experiments on a WT gearbox test rig. Experimental results and comprehensive comparison analysis with respect to the traditional CNN and traditional multiscale feature extractors have demonstrated the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Abstract In this study, we proposed a novel anti-aggregation of gold nanoparticles (AuNPs) strategy for colorimetric sensing of iodide ions (I−) regulated by the redox reaction between the target ions and the ion cross-linking agent. Cu2+ as interlinking ion can induce aggregation of arginine capped AuNPs (Arg-AuNPs) due to the formation of Arg-Cu2+-Arg analogous structure resulting from the chelation between Cu2+ and arginine, with a clear color change of solution from red to blue. In the presence of I−, however, Cu2+ would be readily reduced owing to the formation of CuI, AuNPs underwent a transformation from an aggregation to a dispersion state depending on the concentration of I−, leading color changes from blue to red. The corresponding color variation in the process of anti-aggregation of AuNPs can be monitored through UV–vis spectrophotometer or by the naked-eye, making quantitative analysis of I− feasible in a convenient colorimetric or visual way. The assay only took 5 min, showing high sensitivity with a lowest detectable concentration of 10 nM and excellent selectivity for I− over other anions tested, which was successfully applied for the detection of I− in drinking water and table salt samples. Graphical abstract Image 1 Highlights • A facile and sensitive colorimetric assay for detecting of I− in water was proposed. • The strategy was based on a redox-regulated anti-aggregation of AuNPs in the presence of Cu2+. • The anti-aggregation process can be monitored through UV-vis spectrophotometer or by the naked-eye. • This assay showed high sensitivity and exhibited good selectivity towards I− over other anions. [ABSTRACT FROM AUTHOR]

This paper studies the current sharing problem of a dc microgrid using the hybrid dynamic control method. The hybrid dynamic controller framework is established including a continuous-time part and a discrete-time part, where the former part eliminates the voltage deviation of the dc bus and the latter part ensures the current sharing accuracy of the dc microgrid. The proposed distributed hybrid secondary controller not only guarantees a high accuracy of current sharing but also maintains the voltage regulation at the dc bus. Different from most existing methods, it only utilizes the sampling output current information of neighbors at the discrete time instants, which greatly reduces the communication burden. Under the framework of stability analysis on the closed-loop system, the proposed hybrid dynamic controller achieves both current sharing and voltage regulation if the average interacted interval of the discrete time interaction satisfies a bounded constraint. Besides, a detailed parameter design of the controller is provided. Finally, simulation and experimental tests are presented to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, we develop a novel optimal control strategy for a class of uncertain nonlinear systems with unmatched interconnections. To begin with, we present a stabilizing feedback controller for the interconnected nonlinear systems by modifying an array of optimal control laws of auxiliary subsystems. We also prove that this feedback controller ensures a specified cost function to achieve optimality. Then, under the framework of adaptive critic designs, we use critic networks to solve the Hamilton–Jacobi–Bellman equations associated with auxiliary subsystem optimal control laws. The critic network weights are tuned through the gradient descent method combined with an additional stabilizing term. By using the newly established weight tuning rules, we no longer need the initial admissible control condition. In addition, we demonstrate that all signals in the closed-loop auxiliary subsystems are stable in the sense of uniform ultimate boundedness by using classic Lyapunov techniques. Finally, we provide an interconnected nonlinear plant to validate the present control scheme. [ABSTRACT FROM AUTHOR]

The fluorescence of CDs was dramatically quenched in GSH-AuNPs solutions based on FRET, and then the fluorescent intensity was effectively recovered with the addition of BPO. The detection of BPO was achieved using GSH-AuNPs / CDs as nanoprobe accompanying with GSH-AuNPs from dispersion state to aggregation state. [Display omitted] • A sensitive FRET probe based on GSH-AuNPs / CDs is fabricated for BPO detection. • Sensitive and selective detection of BPO is achieved by regulating the FRET effect. • It offers a facile alternative for monitoring BPO additive amount in food. Herein, a sensitive fluorescence nanoplatform for benzoyl peroxide (BPO) detection is constructed from carbon dots (CDs) and glutathione capped gold nanoparticles (GSH-AuNPs). The fluorescence of CDs is first quenched due to the fluorescence resonance energy transfer (FRET) effect in the presence of GSH-AuNPs, and then effectively recovered when adding BPO. The detection mechanism lies in the aggregation of AuNPs in a high salt background due to oxidation of GSH caused by BPO, thus the amount of BPO is reflected by the variations of the recovered signals. The linear range and detection limit in this detection system is found to be 0.05–200 μM (R2 = 0.994) and 0.1 µg g−1 (3σ/K), respectively. Several possible interferents with high concentration show little influence on BPO detection. The proposed assay exhibits good performance for BPO determination in wheat flour and noodles, demonstrating its applicability for facile monitoring BPO additive amount in real foods. [ABSTRACT FROM AUTHOR]

Summary: In this paper, we develop a novel event‐triggered robust control strategy for continuous‐time nonlinear systems with unmatched uncertainties. First, we build a relationship to show that the event‐triggered robust control can be obtained by solving an event‐triggered nonlinear optimal control problem of the auxiliary system. Then, within the framework of reinforcement learning, we propose an adaptive critic approach to solve the event‐triggered nonlinear optimal control problem. Unlike typical actor‐critic dual approximators used in reinforcement learning, we employ a unique critic approximator to derive the solution of the event‐triggered Hamilton‐Jacobi‐Bellman equation arising in the nonlinear optimal control problem. The critic approximator is updated via the gradient descent method, and the persistence of excitation condition is necessary. Meanwhile, under a newly proposed event‐triggering condition, we prove that the developed critic approximator update rule guarantees all signals in the auxiliary closed‐loop system to be uniformly ultimately bounded. Moreover, we demonstrate that the obtained event‐triggered optimal control can ensure the original system to be stable in the sense of uniform ultimate boundedness. Finally, a F‐16 aircraft plant and a nonlinear system are provided to validate the present event‐triggered robust control scheme. [ABSTRACT FROM AUTHOR]

This paper presents a novel robust regulation method for a class of continuous-time nonlinear systems subject to unmatched perturbations. To begin with, the robust regulation problem is transformed into an optimal regulation problem by constructing a value function for the auxiliary system. Then, a simultaneous policy iteration (SPI) algorithm is developed to solve the optimal regulation problem within the framework of adaptive dynamic programming. To implement the SPI algorithm, actor and critic networks are employed to approximate the optimal control and the optimal value function, respectively, and the Monte Carlo integration method is applied to obtain the unknown weight parameters. Finally, two examples, including a power system, are provided to demonstrate the applicability of the developed approach. [ABSTRACT FROM PUBLISHER]

This paper proposes two new definitions and related theorems in analyzing the transient behavior of terminal sliding mode control (TSMC) for nonlinear systems. The first one is named critical trajectory (CT), which is used to characterize the system dynamics for both TSMC and its nonsingular version, i.e., nonsingular TSMC (NTSMC). The second one is named constrained surface (CS), which is used to characterize the phase trajectory for NTSMC. Based on these two terms, we further propose two new theorems and their associated rigorous proofs that can be used to comprehensively describe the dynamic behavior of TSMC and NTSMC. In addition to theoretical analyses, we also present two case studies, i.e., one numerical example and one two-link manipulator system, to verify the effectiveness of the proposed theoretical research. [ABSTRACT FROM AUTHOR]

This paper presents a novel adaptive dynamic programming(ADP)-based self-learning robust optimal control scheme for input-affine continuous-time nonlinear systems with mismatched disturbances. First, the stabilizing feedback controller for original nonlinear systems is designed by modifying the optimal control law of the auxiliary system. It is also demonstrated that this feedback controller can optimize a specified value function. Then, within the framework of ADP, a single critic network is constructed to solve the Hamilton–Jacobi–Bellman equation associated with the auxiliary system optimal control law. To update the critic network weights, an indicator function and a concurrent learning technique are employed. By using the proposed update law for the critic network, the restrictive conditions including the initial admissible control and the persistence of excitation condition are relaxed. Moreover, the stability of the closed-loop auxiliary system is guaranteed in the sense that all the signals are uniformly ultimately bounded. Finally, the applicability of the developed control strategy is illustrated through simulations for an unstable nonlinear plant and a power system. [ABSTRACT FROM AUTHOR]

In this study, the cooperative output regulation problem for heterogeneous multi‐agent systems is addressed by considering a leader dynamics subject to bounded (possibly non‐zero, persistent, and time varying) inputs. Compared to many existing works with a leader of zero input, using such a leader dynamics will facilitate realisation of more diverse and sophisticated tracking trajectories for cooperative output regulation control. However, it also poses a challenge to pursue exact output regulation performance. To this end, a new two‐layer hierarchical design framework is proposed. This framework consists of an upper‐layer cooperative estimator for estimating the leader's state information in finite time, and a lower‐layer distributed output regulator to achieve exact output regulation performance. Both finite‐time estimation and asymptotic output regulation performance are analysed using the Lyapunov function method, and the associated solvability conditions are established as a set of linear matrix inequalities plus linear matrix equations. Simulation studies are also included to demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

This paper presents two adaptive ensemble sampling approaches for imbalanced learning: one is the undersampling-based approach, and the other one is the oversampling-based approach, with the objectives of bias reduction and adaptive learning. Both of these two approaches are based on a novel class imbalance metric, termed generalized imbalance ratio (GIR), instead of the conventional sample size ratio. Specifically, these two sampling-based approaches adaptively split the imbalanced learning problem into multiple balanced learning subproblems in a probabilistic way, which forces the classifiers trained in the subproblems focus on those difficult to learn samples. In each subproblem, several weak classifiers are trained in a boosting manner. A final stronger classifier is further built by combining all these weak classifiers in a bagging manner. Extensive experiments are conducted on real-life UCI imbalanced data sets to evaluate the performance of the proposed methods. The superior performance demonstrates the effectiveness of the proposed methods and indicates wide potential applications in data mining. [ABSTRACT FROM AUTHOR]

There is spatio‐temporal nature for many multi‐agent systems such as infight hose‐and‐drogue aerial refuelling systems. To deal with consensus control of such cases, this study establishes a non‐linear leader‐following spatio‐temporal multi‐agent system modelled by partial differential equations. Initially, a boundary controller based on boundary coupling is studied to ensure consensus of the multi‐agent system. A sufficient condition on the existence of the controller for consensus is presented in terms of linear matrix inequalities. To simplify the obtained result, a second boundary controller is studied and a simple sufficient condition of its existence is investigated. Finally, two numerical examples demonstrate the effectiveness of the proposed methods. The merits of the proposed controllers lie in making use of only spatial boundary communication and requiring actuators and sensors only at spatial boundary positions. [ABSTRACT FROM AUTHOR]

By employing neural network approximation architecture, the nonlinear discounted optimal regulation is handled under event-driven adaptive critic framework. The main idea lies in adopting an improved learning algorithm, so that the event-driven discounted optimal control law can be derived via training a neural network. The stability guarantee and simulation illustration are also included. It is highlighted that the initial stabilizing control policy is not required during the implementation process with the combined learning rule. Moreover, the closed-loop system is formulated as an impulsive model. Then, the related stability issue is addressed by using the Lyapunov approach. The simulation studies, including an application to a power system, are also conducted to verify the effectiveness of the present design method. [ABSTRACT FROM PUBLISHER]

Currently, vibration analysis has been widely considered as an effective way to fulfill the fault diagnosis task of gearboxes in wind turbines (WTs). However, vibration signals are usually with abundant noise and characterized as nonlinearity and nonstationarity. Therefore, it is quite challenging to extract robust and useful fault features from complex vibration signals to achieve an accurate and reliable diagnosis. This paper proposes a novel feature representation learning approach, named stacked multilevel-denoising autoencoders (SMLDAEs), with the aim to learn robust and discriminative fault feature representations through a deep network architecture for diagnosis accuracy improvement. In our proposed approach, we design an MLD training scheme, which uses multiple noise levels to train AEs. It enables to learn more general and detailed fault feature patterns simultaneously at different scales from the complex frequency spectra of the raw vibration data, and therefore helps enhance the feature learning and fault diagnosis capability. Furthermore, SMLDAE-based fault diagnosis is performed with an unsupervised representation learning procedure followed by a supervised fine-tuning process with label information for classification. Our approach is evaluated by using the field vibration data collected from a self-designed WT gearbox test rig. The results show that our proposed approach learned more robust and discriminative fault feature representations and achieved the best diagnosis accuracy compared with the traditional approaches. [ABSTRACT FROM PUBLISHER]

The design of robust controllers for continuous‐time (CT) non‐linear systems with completely unknown non‐linearities is a challenging task. The inability to accurately identify the non‐linearities online or offline motivates the design of robust controllers using adaptive dynamic programming (ADP). In this study, an ADP‐based robust neural control scheme is developed for a class of unknown CT non‐linear systems. To begin with, the robust non‐linear control problem is converted into a non‐linear optimal control problem via constructing a value function for the nominal system. Then an ADP algorithm is developed to solve the non‐linear optimal control problem. The ADP algorithm employs actor‐critic dual networks to approximate the control policy and the value function, respectively. Based on this architecture, only system data is necessary to update simultaneously the actor neural network (NN) weights and the critic NN weights. Meanwhile, the persistence of excitation assumption is no longer required by using the Monte Carlo integration method. The closed‐loop system with unknown non‐linearities is demonstrated to be asymptotically stable under the obtained optimal control. Finally, two examples are provided to validate the developed method. [ABSTRACT FROM AUTHOR]

This paper presents a simple and effective density-based outlier detection approach with local kernel density estimation (KDE). A Relative Density-based Outlier Score (RDOS) is introduced to measure local outlierness of objects, in which the density distribution at the location of an object is estimated with a local KDE method based on extended nearest neighbors of the object. Instead of using only k nearest neighbors, we further consider reverse nearest neighbors and shared nearest neighbors of an object for density distribution estimation. Some theoretical properties of the proposed RDOS including its expected value and false alarm probability are derived. A comprehensive experimental study on both synthetic and real-life data sets demonstrates that our approach is more effective than state-of-the-art outlier detection methods. [ABSTRACT FROM AUTHOR]

The authors focus on developing adaptive‐critic‐based near‐optimal controllers to solve continuous‐time non‐linear decentralised feedback stabilisation problems. The decentralised feedback control problem with respect to the matched interconnected systems is addressed by designing the optimal controllers of the corresponding isolated subsystems. By employing a novel updating rule to reduce the requirement about the initial stabilising control, the adaptive‐critic‐based near‐optimal feedback controllers can be obtained with an excellent approximation property. The closed‐loop form of each isolated subsystem is constructed and its stability is handled by incorporating the improved learning mechanism. A simulation example is also conducted to verify the decentralised control performance of the present approach. [ABSTRACT FROM AUTHOR]

A boronate-decorated nanomagnetic organic-inorganic hybrid material was facilely synthesized by utilizing the nanomagnetic polyhedral oligomeric silsesquioxanes (POSS) composite (Fe 3 O 4 @POSS) as the base platform. A simple copolymerization occurred between 3-acrylamidophenylboronic acid (AAPBA) and the residual end vinyl groups supplied by the substrate. Here the special emphasis was placed on the octavinyl POSS, which not only acted as the building blocks for a hybrid architecture but also facilitated the process of grafting boronate groups onto the surface of POSS based nanomagnetic composite (Fe 3 O 4 @POSS). The successful immobilization of affinity ligand-AAPBA on the Fe 3 O 4 @POSS was confirmed by Fourier transform infrared (FT-IR), elemental analysis, inductively coupled plasma atomic emission spectrometer (ICP-AES), field emission scanning electron microscope. A magnetic solid-phase extraction (MSPE) for cis -diols enrichment was developed using the as-prepared Fe 3 O 4 @POSS-AAPBA material as an affinity sorbent and three catecholamines (CAs), namely noradrenaline, epinephrine and isoprenaline, as model analytes. Under the optimal extraction conditions, sensitive and simultaneous analysis of three CAs from the urine sample was achieved by high-performance liquid chromatography with UV detection (HPLC-UV). The limits of detection (LOD, S/N = 3) and the limits of quantitation (LOQ, S/N = 10) for the target analytes were 0.81–1.32 ng mL −1 and 2.70–4.40 ng mL −1 , respectively. Also good recoveries (85.5–101.7%) and repeatability (RSD≤10.1%) were obtained by this method. This work not only showed a facility for the utilization of Fe 3 O 4 @POSS as a substrate for constructing a boronate functionalized nanomagnetic sorbent, but also demonstrated the capability of the derived material for recognition of trace amount of cis -diols biomolecules presented in complicated biological matrices. [ABSTRACT FROM AUTHOR]

In this work, a La3+ assisted glutathione-capped gold nanoclusters and carbon dots (GSH-Au NCs/CDs) nanoplatform for sensitive detection of fenthion (FEN) is fabricated. The fluorescence response of GSH-Au NCs significantly increases due to aggregation-induced emission enhancement (AIEE) effect induced by La3+, which is further enhanced with adding FEN due to the coordination between La3+ and FEN. Taking the fluorescence intensity of CDs as the signal background, the ratiometric fluorescence of GSH-Au NCs and CDs has a good linear relationship with the FEN concentration from 0.01 to 1.10 μg mL−1, and detecting FEN exhibits a good sensitivity at a low detection limit of 6.74 ng g−1. The La3+ assisted GSH-Au NCs/CDs nanoplatform demonstrates desirable selectivity and applicability for monitoring trace level of FEN in fruit and vegetable samples. The non-enzymatic strategy by taking advantage of successive AIEE of GSH-Au NCs has a great potential for facile screening organophosphate pesticides in agro-products. [Display omitted] • A non-enzymatic ratiometric fluorescence probe for FEN is facilely fabricated. • Sensitive detection of FEN is realized by La3+ induced successive AIEE of Au NCs. • The La3+-CDs/Au NCs system is applicable for FEN residue analysis in agro-products. [ABSTRACT FROM AUTHOR]

• Diel lake hydrochemical variations and the coupled carbon cycling were observed. • These processes were controlled mainly by lake metabolic processes. • High DIC in a karst lake may support high primary production. • The carbon sink by the coupled carbonate weathering reached 650–704 t C km−2 yr−1. • A karst aquatic system can maintain net autotrophy. The precipitation of carbonate minerals does not invariably result in CO 2 emission to the atmosphere, because dissolved inorganic carbon (DIC) can be partially utilized by terrestrial aquatic phototrophs, thus generating an autochthonous organic carbon (AOC) sink. However, little is known about the potential effects of this mechanism on carbon cycles in DIC-rich lakes, mainly due to the lack of detailed documentation of the related processes, which limits our ability to accurately evaluate and predict the magnitude of this carbon sink. We conducted field observations in Fuxian Lake, a large and representative karst lake in the Yunnan-Guizhou Plateau, SW China. Continuous diel monitoring was conducted to quantitatively assess the coupled relationship between lake metabolism and DIC cycling and its influence on the carbonate weathering-related CO 2 sink. We found that the diel physicochemical variations and isotopic characteristics were mainly controlled by the metabolism of aquatic phototrophs, evidenced by a significant relationship between net ecosystem production and diel DIC cycling, and demonstrating the significance of DIC fertilization in supporting high primary production in karst lakes. The data showed that a reduction in photosynthesis occurred in the afternoon of almost every day, which can be explained by the lower CO 2 /O 2 ratio that increased the potential for the photorespiration of aquatic plants, thus reducing photosynthesis. We found that a net autotrophic ecosystem prevailed in Fuxian Lake, suggesting that the lake functions more as a sink than a source of atmospheric CO 2. Considering carbonate weathering, the estimated AOC sink amounted to 650–704 t C km−2 yr−1, demonstrating both the potentially significant role of metabolism in lacustrine carbon cycling and the potential of the combination of photosynthesis and carbonate weathering for carbon sequestration. Our findings may help to quantitatively estimate the future impact of lake metabolism on carbon cycling, with implications for formulating management policies needed to regulate the magnitude of this carbon sink. [Display omitted] [ABSTRACT FROM AUTHOR]

In this paper, we present a Bayesian classification approach for automatic text categorization using class-specific features. Unlike conventional text categorization approaches, our proposed method selects a specific feature subset for each class. To apply these class-specific features for classification, we follow Baggenstoss's PDF Projection Theorem (PPT) to reconstruct the PDFs in raw data space from the class-specific PDFs in low-dimensional feature subspace, and build a Bayesian classification rule. One noticeable significance of our approach is that most feature selection criteria, such as Information Gain (IG) and Maximum Discrimination (MD), can be easily incorporated into our approach. We evaluate our method's classification performance on several real-world benchmarks, compared with the state-of-the-art feature selection approaches. The superior results demonstrate the effectiveness of the proposed approach and further indicate its wide potential applications in data mining. [ABSTRACT FROM PUBLISHER]