East China Jiaotong University

The paper describes the process of building data warehouses. It discusses the functions and main points of data warehouse, and the affections on decision support system.

Deep learning has achieved great successes in conventional computer vision tasks. In this paper, we exploit deep learning techniques to address the hyperspectral image classification problem. In contrast to conventional computer vision tasks that only examine the spatial context, our proposed method can exploit both spatial context and spectral correlation to enhance hyperspectral image classification. In particular, we advocate four new deep learning models, namely, 2-D convolutional neural network (2-D-CNN), 3-D-CNN, recurrent 2-D CNN (R-2-D-CNN), and recurrent 3-D-CNN (R-3-D-CNN) for hyperspectral image classification. We conducted rigorous experiments based on six publicly available data sets. Through a comparative evaluation with other state-of-the-art methods, our experimental results confirm the superiority of the proposed deep learning models, especially the R-3-D-CNN and the R-2-D-CNN deep learning models.

The application of visible (Vis; 400–750 nm) and near infrared red (NIR; 750–2500 nm) region spectroscopy to assess fruit and vegetables is reviewed in context of ‘point’ spectroscopy, as opposed to multi- or hyperspectral imaging. Vis spectroscopy targets colour assessment and pigment analysis, while NIR spectroscopy has been applied to assessment of macro constituents (principally water) in fresh produce in commercial practice, and a wide range of attributes in the scientific literature. This review focusses to key issues relevant to the widespread implementation of Vis-NIR technology in the fruit sector. A background to the concepts and technology involved in the use of Vis-NIR spectroscopy is provided and instrumentation for in-field and in-line applications, which has been available for two and three decades, respectively, is described. A review of scientific effort is made for the period 2015 - February 2020, in terms of the application areas, instrumentation, chemometric methods and validation procedures, and this work is critiqued through comparison to techniques in commercial use, with focus to wavelength region, optical geometry, experimental design, and validation procedures. Recommendations for future research activity in this area are made, e.g., application development with consideration of the distribution of the attribute of interest in the product and the matching of optically sampled and reference method sampled volume; instrumentation comparisons with consideration of repeatability, optimum optical geometry and wavelength range). Recommendations are also made for reporting requirements, viz. description of the application, the reference method, the composition of calibration and test populations, chemometric reporting and benchmarking to a known instrument/method, with the aim of maximising useful conclusions from the extensive work being done around the world.

Design methods and applications of nanocomposite hydrogel-based strain and pressure sensors have been summarized and classified in this review.

Conductive hydrogels have become one of the most promising materials for skin-like sensors because of their excellent biocompatibility and mechanical flexibility. However, the limited stretchability, low toughness, and fatigue resistance lead to a narrow sensing region and insufficient durability of the hydrogel-based sensors. In this work, an extremely stretchable, highly tough, and anti-fatigue conductive nanocomposite hydrogel is prepared by integrating hydrophobic carbon nanotubes (CNTs) into hydrophobically associated polyacrylamide (HAPAAm) hydrogel. In this conductive hydrogel, amphiphilic sodium dodecyl sulfate was used to ensure uniform dispersion of CNTs in the hydrogel network, and hydrophobic interactions between the hydrogel matrix and the CNT surface formed, greatly improving the mechanical properties of the hydrogel. The obtained CNTs/HAPAAm hydrogel showed excellent stretchability (ca. 3000%), toughness (3.42 MJ m–3), and great anti-fatigue property. Moreover, it exhibits both high tensile strain sensitivity in the wide strain ranges (gauge factor = 4.32, up to 1000%) and high linear sensitivity (0.127 kPa–1) in a large-pressure region within 0–50 kPa. The CNTs/HAPAAm hydrogel-based sensors can sensitively and stably detect full-range human activities (e.g., elbow rotation, finger bending, swallowing motion, and pronouncing) and handwriting, demonstrating the CNTs/HAPAAm hydrogel’s potential as the wearable strain and pressure sensors for flexible devices.

/BC composite films for efficient EMI shielding to address EMI problems of a fast-developing modern society.

The plasmon-induced transparency (PIT), which is destructive interference between the superradiation mode and the subradiation mode, is studied in patterned graphene-based terahertz metasurface composed of graphene ribbons and graphene strips. As the results of finite-difference time-domain (FDTD) simulation and coupled-mode theory (CMT) fitting, the PIT can be dynamically modulated by the dual-mode. The left (right) transmission dip is mainly tailored by the gate voltage applied to graphene ribbons (stripes), respectively, meaning a dual-mode on-to-off modulator is realized. Surprisingly, an absorbance of 50% and slow-light property of 0.7 ps are also achieved, demonstrating the proposed PIT metasurface has important applications in absorption and slow-light. In addition, coupling effects between the graphene ribbons and the graphene strips in PIT metasurface with different structural parameters also are studied in detail. Thus, the proposed structure provides a new basis for the dual-mode on-to-off multi-function modulators.

Complicated weather conditions lead to intermittent, random and volatility in photovoltaic (PV) systems, which makes PV predictions difficult. A recurrent neural network (RNN) is considered to be an effective tool for time-series data prediction. However, when the weather changes intensely, the long-term sequence of multivariate may cause gradient vanishing (exploding) during the training of RNN, leading the prediction results to local optimum. Long short-term memory (LSTM) network is the deep structure of RNN. Due to its special hidden layer unit structure, it can preserve the trend information contained in the long-term sequence, which is allowed to solve the problems of RNN and improve performance. An LSTM-based approach is applied for short-term predictions in this study based on a timescale that encompasses global horizontal irradiance (GHI) one hour in advance and one day in advance. Inaccurate forecasts usually occur on cloudy days, and the results of ANN and SVR in the literature prove this. To improve prediction accuracy on cloudy days, the clearness-index was introduced as an input data for the LSTM model and to classify the type of weather by k-means during the data processing, where cloudy days are classified as the cloudy and the mixed(partially cloudy). NN models are established to compare the accuracy of different approaches and the cross-regional study is to prove whether the method can be generalizable. From the results of hourly forecast, the R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> coefficient of LSTM on cloudy days and mixed days is exceeding 0.9, while the R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of RNN is only 0.70 and 0.79 in Atlanta and Hawaii. From the results of daily forecast, All R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> on cloudy days is about 0.85. However, the LSTM is still very effective in improving of RNN and more accurate than other models.

As a legacy from conventional wireless services, illegal eavesdropping is regarded as one of the critical security challenges in Connected and Autonomous Vehicles (CAVs) network. Our work considers the use of Distributed Kalman Filtering (DKF) and Deep Reinforcement Learning (DRL) techniques to improve anti-eavesdropping communication capacity and mitigate jamming interference. Aiming to improve the security performance against smart eavesdropper and jammer, we first develop a DKF algorithm that is capable of tracking the attacker more accurately by sharing state estimates among adjacent nodes. Then, a design problem for controlling transmission power and selecting communication channel is established while ensuring communication quality requirements of the authorized vehicular user. Since the eavesdropping and jamming model is uncertain and dynamic, a hierarchical Deep Q-Network (DQN)-based architecture is developed to design the anti-eavesdropping power control and possibly channel selection policy. Specifically, the optimal power control scheme without prior information of the eavesdropping behavior can be quickly achieved first. Based on the system secrecy rate assessment, the channel selection process is then performed when necessary. Simulation results confirm that our jamming and eavesdropping defense technique enhances the secrecy rate as well as achievable communication rate compared with currently available techniques.

Zwitterionic hydrogels exhibit eminent nonfouling and hemocompatibility. Several key challenges hinder their application as coating materials for blood-contacting biomedical devices, including weak mechanical strength and low adhesion to the substrate. Here, we report a poly(carboxybetaine) microgel reinforced poly(sulfobetaine) (pCBM/pSB) pure zwitterionic hydrogel with excellent mechanical robustness and anti-swelling properties. The pCBM/pSB hydrogel coating was bonded to the PVC substrate via the entanglement network between the pSB and PVC chain. Moreover, the pCBM/pSB hydrogel coating can maintain favorable stability even after 21 d PBS shearing, 0.5 h strong water flushing, 1000 underwater bends, and 100 sandpaper abrasions. Notably, the pCBM/pSB hydrogel coated PVC tubing can not only mitigate the foreign body response but also prevent thrombus formation ex vivo in rats and rabbits blood circulation without anticoagulants. This work provides new insights to guide the design of pure zwitterionic hydrogel coatings for biomedical devices.

Vehicle-to-vehicle (V2V) communication applications face significant challenges to security and privacy since all types of possible breaches are common in connected and autonomous vehicles (CAVs) networks. As an inheritance from conventional wireless services, potential eavesdropping is one of the main threats to V2V communications. In our work, the anti-eavesdropping scheme in CAVs networks is developed through the use of cognitive risk control (CRC)-based vehicular joint radar-communication (JRC) system. In particular, the supplement of off-board measurements acquired using V2V links to the perceptual information has presented the potential to enhance the traffic target positioning precision. Then, transmission power control is performed utilizing reinforcement learning, the result of which is determined by a task switcher. Based on the threat evaluation, a multiple armed bandit problem is designed to implement the secret key switching procedure when it is needed. Through constant perception-execution loops (PELs), the security and confidentiality is improved for the authorized vehicles in their behavioral interactions with the illegal eavesdropper. Numerical experiments have presented that the developed approach has anticipated performance in terms of some risk assessment indicators.

Solar energy absorption is a very important field in photonics. The successful development of an efficient, wide-band solar absorber is an extremely powerful driver in this field. We propose an ultra-wideband (UWB) solar energy absorber composed of a Ti ring and SiO2-Si3N4-Ti thin films. In the range of 300-4000 nm, the wide band has an absorption efficiency of more than 90% and can reach 3683 nm, and it has four absorption peaks with a high absorptivity. Moreover, the weighted average absorption efficiency of the solar absorber under AM 1.5 is maintained above 97.03%, which indicates it has great potential for use in the field of solar energy absorption. Moreover, we proved that the polarization is insensitive by analyzing the absorption characteristics at arbitrary polarization angles. For both the transverse electric (TE) and transverse magnetic (TM) modes, the UWB absorption is maintained at more than 90% in the wide incidence angle range of 60°. The UWB solar energy absorber has great potential for use in a variety of applications, such as converting solar light and heat into electricity for public use and reducing the side effects of coal-fired power generation. It can also be used in information detection and infrared thermal imaging owing to its UWB characteristics.

The insulator is an important catenary component that maintains the insulation between the catenary and earth. Due to the long-term impact of railway vehicles and the environment, defects in the insulator are inevitable. Recently, automatic catenary inspection using computer vision and pattern recognition has been introduced to improve the safety of railway operation. However, achieving full automation of insulator defect detection is still very challenging due to the visual complexity of defects and the small number of defective insulators. To overcome these problems, this paper proposes a novel insulator surface defect detection system using a deep convolutional neural network (CNN). The proposed system consists of two stages. First, a Faster R-CNN network is adopted to localize the key catenary components, and the image areas that contain the insulators are obtained. Then, the classification score and anomaly score are determined from a deep multitask neural network that is composed of a deep material classifier and a deep denoising autoencoder. The defect state is determined by analyzing the classification score and anomaly score. Experiments of the catenary insulator defect detection along the Hefei-Fuzhou high-speed railway line indicate that the system can achieve high detection accuracy.

Memristor is an ideal electronic device used as an artificial nerve synapse due to its unique memory function. This article presents a design of a new Hopfield neural network (HNN) that can generate multiscroll attractors by utilizing a new memristor as a synapse in the HNN. Differing from the others, this memristor is constructed with hyperbolic tangent functions. Taking the memristor as a self-feedback synapse of a neuron in the HNN, the memristive HNN can yield multidouble-scroll attractors, and its parameters can be used to effectively control the number of double scrolls contained in an attractor. Interestingly, the generation of multidouble-scroll attractors is independent of the memductance function but depends only on the internal state equation. Thus, the memductance function can be adjusted to yield various complex dynamical behaviors. Moreover, amplitude control effects and quantitatively controllable multistability are revealed by numerical analysis. The accurate reproduction of some dynamical behaviors by a designed circuit verifies the correctness of the numerical analysis. Finally, based on the proposed memristive HNN, a novel image encryption scheme in the 3-D setting is designed and evaluated, demonstrating its good encryption performances.

Vortex beams have been extensively realized using different approaches. Typically, the efficiency and bandwidth of a vortex beam are limited by impure copolarized components and the intrinsic dispersion of passive resonant structures. Here, we propose a strategy to generate wideband vortex beams by using a Pancharatnam-Berry metasurface in which two orthogonal reflections exhibit a broadband out-of-phase difference. To achieve this, a broadband strategy based on multimode operation and dispersion engineering methods was established. A dual-layer meta-atom is proposed; each layer comprises of five metallic dipoles, and the geometrical parameters are carefully adjusted to tune the resonant frequencies. Because the dipole orientations in each layer are orthogonal, the reflection responses under the two orthogonal polarizations can be independently engineered. Both numerical and experimental results indicate that our method not only enables a high-efficiency spiral beam conversion over a broad range of 6.95-18 GHz (>82%) but also causes a polarization-insensitive effect; thus, it can be adapted for any linear or circular polarization.

An ultrahigh arsenic uptake capacity was achieved using a hierarchically porous UiO-66 with tunable mesopores and active sites.

This study aims to evaluate the impacts of international tourism development and green technology innovation on economic growth and carbon dioxide emissions in the top 10 GDP countries between 1995 and 2018. Our preliminary findings reject the preposition of data normality, which instigate us to apply a novel method of moments quantile regression. The overall results suggest that international tourism development facilitates economic growth and increases carbon dioxide emissions asymmetrically across the different levels of economic growth and carbon dioxide emissions. Specifically, the economic growth impacts are relatively large for the comparatively more developed nations while the adverse environmental impacts are relatively larger for the comparatively less-polluted nations; thus, the tourism led-economic growth hypothesis is verified. On the other hand, green technology innovation is found to facilitate economic growth and mitigate carbon dioxide emissions, especially in the context of the relatively more developed and polluted economies.

Photo-crosslinkable gelatin methacrylate (GelMA) has become an attractive ink in 3D printing due to its excellent biological performance. However, limited by low viscosity and long cross-linking time, it is still a challenge to directly print GelMA by extrusion-based 3D printing. Here, to balance the printability and biocompatibility, biomaterial ink composed of GelMA and nanoclay was specially designed. Using this ink, complex scaffolds with high shape fidelity can be easily printed based on the thixotropic property of nanoclay. In this study, we tried to answer some basic printing-required questions of this ink, including the printability window, general properties (porosity, mechanical strength, et al), and biocompatibility. We found that the GelMA/Nanoclay ink enabled printing complex 3D scaffolds, such as a bionic ear and a branched vessel. Furthermore, the addition of nanoclay improved the porosity, increased the mechanical strength, reduced the degradation ratio, and maintained a good biocompatibility of the printed scaffolds. Therefore, this method offers an easy way to print complex scaffolds with good shape fidelity and biological performance, and it might open up new potential applications for the customized therapy of tissue defects.

film phase transition process. The impedance matching theory is applied to explain the high level of absorption generated by the absorber. Finally, the effects of the structural parameters on the performance of the absorber are analysed. This work will have many applications in the terahertz field and offers a wide range of ideas for the design of terahertz-enabled devices.

There are two common challenges in particle swarm optimization (PSO) research, that is, selecting proper exemplars and designing an efficient learning model for a particle. In this article, we propose a triple archives PSO (TAPSO), in which particles in three archives are used to deal with the above two challenges. First, particles who have better fitness (i.e., elites) are recorded in one archive while other particles who offer faster progress, called profiteers in this article, are saved in another archive. Second, when breeding each dimension of a potential exemplar for a particle, we choose a pair of elite and profiteer from corresponding archives as two parents to generate the dimension value by ordinary genetic operators. Third, each particle carries out a specific learning model according to the fitness of its potential exemplars. Furthermore, there is no acceleration coefficient in TAPSO aiming to simplify the learning models. Finally, if an exemplar has excellent performance, it will be regarded as an outstanding exemplar and saved in the third archive, which can be reused by inferior particles aiming to enhance the exploitation and to save computing resources. The experimental results and comparisons between TAPSO and other eight PSOs on 30 benchmark functions and four real applications suggest that TAPSO attains very promising performance in different types of functions, contributing to both higher solution accuracy and faster convergence speed. Furthermore, the effectiveness and efficiency of these new proposed strategies are discussed based on extensive experiments.