Search

The attention-based SeriesNet (A-SeriesNet) combined augmented attention residual learning module-based convolutional neural network (augmented ARLM-CNN) subnetwork with hidden state attention module-based recurrent neural network (HSAM-RNN) subnetwork for conditional time series prediction with high accuracy. The augmented ARLM-CNN subnetwork has defects in extracting latent features of the multi-condition series. The forecasting accuracy will decrease when the feature dimension of the multi-condition series becomes high. The same problem also occurs in the HSAM-RNN subnetwork of A-SeriesNet. The dual-stage attention recurrent neural network (DA-RNN) proved that the attention-based encoder-decoder framework is an effective model for dealing with the above problem. This paper applies the DA-RNN to the HSAM-RNN subnetwork of A-SeriesNet and presents the triple-stage attention-based recurrent neural network (TA-RNN) subnetworks. Furthermore, this paper considers a CNN-based encoder-decoder structure named dual attention residual learning module-based convolutional neural network (DARLM-CNN) subnetwork to improve the augmented ARLM-CNN subnetwork of A-SeriesNet. Finally, this paper presents the triple-stage attention-based SeriesNet (TA-SeriesNet), which uses a new concatenation method instead of the element-wise multiplication of A-SeriesNet to parallel connect the proposed subnetworks and reduce the dependence of forecasting results on a certain subnetwork. The experimental results show our TA-SeriesNet is superior to other deep learning models in forecasting accuracy evaluation metrics for high feature dimensional time series datasets.

PnP problem is well researched in many fields, such as computer vision. It is considered the fundamental method to solve the key problems of robot SLAM. However, in pedestrian visual localization, uncalibrated PnP (UPnP), specifically PnP with unknown focal length (PnPf) is more suitable for solving the problem. Recently, a few researchers proposed some methods to alleviate this problem. However, the localization accuracy of the existing methods is not satisfied when image pixel noise is larger. In other words, RANSAC should be running before solving the PnPf problem to get less noisy input, which means the localization delay increases inevitably. In this paper, we propose a more robust method for solving the PnPf problem without the help of RANSAC based on Gröbner basis and convex optimization. We build a Gröbner basis solver on the offline stage with one instance in the prime field. Then, we substitute the coefficients with real value and find multiple solutions on the online stage. Finally, we construct a convex optimization program to seek the final robust solution to PnPf problem. The other purpose of this paper is to provide a second-level localization experience for the end-user. The simulation result shows that our method can give a localization solution, which is more reliable than benchmark methods by both synthetic and real data verified.

Technology forecasting not only helps business managers to make the right decisions but also helps researchers to grasp the direction of technology development. Technology forecasting, which facilitates the identification of the development technologies with high potential, can be an effective tool to support the management and plan for the future research activities. For this purpose, this paper firstly constructs Multi-modal input based on deep learning (MIDL) text classification model to extract relevant SCI papers from Web of Science database from 1996 to 2019 for topic classification, and then apply the Ensemble Empirical Mode Decomposition (EEMD) and Long Short-Term Memory (LSTM) neural networks to build an EEMD-LSTM technology forecasting model to predict the future development of each research field. Besides, we verify the validity of the method by taking robotics as an example in this paper. The results show that the accuracy, recall and F1 of MIDL text classification model are 0.826, 0.822 and 0.824 respectively. As compared with the optimal results of other classification models, the accuracy, recall and F1 are improved by 4.1%, 3.5%, and 3.8% respectively. The mean MAPE of the EEMD-LSTM model is 7%, which is 11% lower than ARIMA, 8% lower than LSTM, and 10% lower than 2-layer-LSTM.

Inductive wear particle sensors have been widely studied due to their ability to monitor the wear status of equipment in real time. To detect wear particles more precisely, a wear particle sensor based on multiple inductive coils under a toroidal magnetic field is proposed in this paper. With inductive coils located near a stronger magnetic field, the sensor can not only ensure the flow rate, but also enhance wear particle detection accuracy. The proportional relationship between the signal and the wear particle velocity and the excitation current is discussed in this paper. The crosstalk phenomenon among different inductive coils was also investigated by single particle experiments and lubricating oil dynamic experiments. In the dynamic oil experiment, the sensor detected $13~\mu \text{m}$ particles under a flow rate of 570 mL/min, which satisfied most industrial online monitoring demands.

In this paper, the secrecy performance of the physical layer security (PLS) of the hybrid free-space optical/radio frequency (FSO/RF) communication system is analyzed. The transmission protocol of the considered system is performed under the eavesdropper's attempt to overhear the RF link between the transmitter and legitimate receiver of the hybrid system. The FSO link is characterized by Málaga-M distribution while the RF links are modeled by Nakagami-m distribution. The two practical eavesdropping modes considered in this paper include: colluding and non-colluding. Exact closed-form expressions for the system's secrecy outage probability (SOP), the asymptotic of the SOP (SOP∞), the probability of strictly positive secrecy capacity (SPSC), the average secrecy capacity (ASC), and the asymptotic of the ASC (ASC∞), are specifically derived under the influence of both eavesdropper modes. Our derived analytical expressions present an efficient tool to investigate the impact of some channel parameters on the secrecy performance, namely the fading severity of the RF links, atmospheric turbulence severity, pointing error of the FSO link, number of eavesdroppers, and the power of the eavesdropper links. The results show that the increase of the eavesdroppers' number under both modes profoundly degrades the considered system secrecy performance. The accuracy of the numerical results obtained is validated by Monte-Carlo simulations.

This paper considers the economy and reliability of the microgrid cluster system, and proposes a bi-level optimized operation strategy for the microgrid cluster, which aims to improve the economic benefits of the microgrid cluster and reduce the operating risk of microgrid. The upper layer takes the microgrid cluster as the research object, with the goal of minimizing the total operating cost of the system, and establishes the optimal model of the microgrid cluster. The lower layer takes the sub-microgrid as the research object, and establishes the microgrid optimization model with the goal of optimal operating cost and operating risk index. The method of combining mixed integer linear programming and IABC algorithm is used to solve the multi-objective bi-level optimization model, and to provide decision makers with two microgrid dispatching schemes with different focuses. Finally, an example is used to verify the effectiveness of the bi-level optimization strategy and improved algorithm proposed in this paper, as well as the practicability of the two dispatching schemes.

Energy router is an emerging device based on power electronic technology, which can realize the flexible distribution of electric energy in the power system. Therefore, the use of energy routers to improve the operating conditions of the power system not only has broad development prospects, but also brings economic benefits. In this regard, this paper proposes a steady-state model of a single energy router and considers the loss of the DC/DC transformer, establishes a power flow equation with multiple energy routers, and proposes a distribution network power flow alternate iteration that takes into account multiple energy routers Calculation method. A case study of an improved IEEE-33 system with multiple energy routers under different working conditions is carried out. The calculation results show that the alternate iterative power flow calculation method used in this paper is effective and feasible, and it reasonably reflects that the network analysis model with multiple energy routers can achieve stable operation, and it can improve the node voltage and reduce the active power loss of the grid. It makes the operation of the distribution network more flexible.

This paper is concerned with the finite-time annular domain bounded control of Itô-type stochastic systems with Wiener and Poisson random disturbance. First, utilizing different quadratic function methods, some sufficient conditions for finite-time annular domain bounded-ness (FTADB) of the system are achieved. Second, two finite-time annular domain bounded controllers are skillfully developed to ensure the FTADB of the closed-loop system, of which one is state feedback controller and the other is dynamic output feedback controller. Furthermore, an algorithm is provided to deal with the obtained matrix inequalities. Finally, two examples are used to demonstrate the effectiveness of the theorems in this paper.

The complexity of a supply chain makes product safety or quality issues extremely difficult to track, especially for the basic agricultural food supply chains of people’s daily diets. The existing agricultural food supply chains present several major problems, such as numerous participants, inconvenient communication caused by long supply chain cycles, data distrust between participants and the centralized system. The emergence of blockchain technology effectively solves the pain-point problem existing in the traceability system of agricultural food supply chains. This paper proposes a framework based on the consortium and smart contracts to track and trace the workflow of agricultural food supply chains, implement traceability and shareability of supply chains, and break down the information islands between enterprises as much as possible to eliminate the need for the central institutions and agencies and improve the integrity of the transaction records, reliability and security. At the same time, farmers record details of the environment and crop growth data in the InterPlanetary File System (IPFS) and store file IPFS hashes in smart contracts, which not only increases data security but also alleviates the blockchain storage explosion problem. This framework has been applied in Shanwei Lvfengyuan Modern Agricultural Development Co., Ltd. Although there are still many defects, the framework has successfully realized functions such as disintermediation and tracing of agricultural product information through QR codes. Thus, the framework proposed in this paper is of great significance and reference value for enterprises to ensure product quality and safety traceability.

This paper presents the application of different approaches of intelligent controllers based on LAMDA (Learning Algorithm for Multivariate Data Analysis) to perform the trajectory tracking task of a mobile robot Pioneer 3-DX simulated in the Virtual Robot Experimentation Platform V-REP environment. The paper proposes the design of a cascade control strategy composed of two controllers, the external controller based on a feedback linearization for the robot kinematics and the internal controller applied to the robot dynamics where the LAMDA approaches are applied. In this work, it is considered an uncertain dynamic model. Thus, its identification and control are based on a reduced-order model for designing purposes. Finally, the dynamic controller is designed using different controllers based on LAMDA, such as LAMDA-PID, LAMDA-Sliding Mode Control, and Adaptive LAMDA. To perform a comparative analysis between them that includes a conventional PID, SMC, and Fuzzy-PID, different trajectories are examined to evaluate the methods. The obtained results are compared qualitatively and quantitatively to determine which proposal performs the most accurate control and presents the best results in terms of performance.

This paper introduces an energy management strategy design method for a plug-in hybrid electric vehicle based on the data-driven approach and online signal analysis. It includes two parts, mode division strategy design, and power distribution strategy design. Using the random forest in data mining technology to analyze optimization results of dynamic programming can quickly extract key information and establish optimal and understandable mode division strategy with high precision and stability directly. Besides, integrating the classic “Engine optimal operating curve control” strategy with wavelet transform and Markov prediction, which not only enhances the adaptability of the strategy to different driving conditions but also improves the fuel economy by reducing the impact of transient power on the engine operation. At the same time, to improve the prediction accuracy of the algorithm without increasing the computational complexity, this paper adds a prediction result correction function to the first-order Markov prediction model to reduce the impact of slow update of the probability matrix on prediction accuracy. The simulation results show the average prediction error of the improved Markov prediction model is reduced by 5.3% and the new energy management strategy designed reduces fuel consumption by 8.28% at the cost of a small increase in electricity consumption.

This paper discusses impact of recovering missing Electroencephalography (EEG) data on classification accuracy of hand movements using tensor-based methods. Improvement in classification accuracy is important for efficient performance of prosthesis. Classification accuracy relies on quality of the observed data. In practice, observed data is usually incomplete because of disconnection of electrodes and other artefacts, which negatively affect the classification accuracy. In this paper, we employ tensor-based imputation methods (canonical/polyadiac decomposition (CPD), weighted optimization version of CPD (CP-WOPT and Nonnegative Matrix Factorization (NMF)) to recover missing data in EEG signals and apply various classifiers to classify hand movements on recovered data. In particular, structured missing data was considered because that is how data gets missed in real-life data acquisition. Percentage of missing data was changed from 10% to 50%. Classifiers are applied on complete, missing and recovered data explicitly to test the performance of our framework. Results show that mean classification accuracy on complete data, missing data and recovered data was 71%, 53% and 64% respectively which shows applicability of our framework.

In the strapdown inertial navigation system, the accuracy of the solving attitude and position is closely related to the quaternion update algorithm. For this reason, what method is used to update the quaternion has become an important project. At present, the primary method is to update the quaternion by solving the equivalent rotation vector. A new quaternion update method is proposed in this paper. By using the third-order and fifth-order Taylor series to approximate the solution of the quaternion differential equation, two attitude quaternion update equations are derived. For single sample and two samples two cases, the derived formula is completely consistent with the common formula derived based on the equivalent rotation vector method. For the three samples in the coning motion environment, the fifth-order formula is derived in this paper, the error analysis method is applied to assess the accuracy of the formula, the two coefficients of the formula correction is optimized, and the drift rate error and drift rate are calculated, which are compared with the drift rate errors of the optimized three-sample equivalent rotation vector algorithm. The expressions for calculating the drift rate errors of the two are the same, and the calculation results are the same. In order to simplify the calculation, the established fifth-order formula is simplified to fourth-order one in this paper, but the drift rate error and drift rate remain unchanged. Finally, simulations and experiments demonstrate the correctness of the attitude quaternion update method proposed in this paper. The attitude quaternion update method proposed in this paper has certain theoretical research and application value for the attitude and position calculation of strapdown inertial navigation application, as well as the further studies of integrated navigation algorithm, and enriches the theoretical system of inertial navigation.

With the commercialization of 5G, in order to recognize QAM signals, one of the main modulation modes in 5G communication systems, this paper put forward the BP-BSA network model based on bird swarm algorithm (BSA) and BP neural network. Firstly, the instantaneous features and high-order cumulants were selected as the appropriate feature statistics by analyzing the characteristics of MQAM signals. After that, the structure of the BP neural network model was determined, and the initial parameters of the BP neural network were optimized using BSA to accelerate the convergence speed of the network. Finally, the features processed with signal to noise ratio (SNR) disorder were used to train and test the BP neural network model. The BP-BSA network model proposed in this paper applies the bird swarm algorithm to the field of modulation recognition for the first time. And the simulation results show that the recognition accuracies of 16, 32, 64, 128, 256QAM signals in the SNR range of −5 dB to 20 dB all reach above 98%. Compared with the same type algorithms, the algorithm proposed in this paper has good recognition performance.

Small cells (SCs) are expected to be ultra-densely deployed in or close to the traffic hot-spots in the fifth generation (5G) mobile networks to provide wireless capacity cost-effectively. Traffic hot-spots change over time, which means SCs cannot be deployed in a one-off manner as macrocells normally do, rather they should be constructed in a staged process. Hence, mathematical models that capture the time-varying staged-construction process, are urgently needed for operators to effectively predict the construction period, but are currently lacking. In this paper, inspired by the foam bursting process-a natural phenomenon that can be observed in daily life such as hand-washing, we first propose a novel model that can predict the time-varying expectation and logarithmic variance of SC coverage areas. Then, we verify the model by real network deployment cases. Additionally, in order to extract parameters from historical base station deployment data, a parameter estimation algorithm is designed and verified. The findings of the paper reveal that mobile operators should construct ultra-dense SC networks in a staged manner like how larger foams split into smaller ones.

Marketing and corporate social responsibility (CSR) are crucial factors that affect closed-loop supply chain network (CLSCN) equilibrium. And the environment of enterprises’ behaviors often occurs during durations and dynamics. To explore the optimal marketing and CSR strategies in a dynamic multi-period CLSCN system, this paper investigates the dynamic multi-period CLSCN equilibrium problem considering marketing and CSR. A multi-period CLSCN system includes manufacturers, retailers, recyclers, and demand markets. Based on Nash non-cooperative game theory and variational inequality, we design the optimal behavior and equilibrium conditions of members. Then, a new equilibrium model of a multi-period CLSCN is constructed. In this model, marketing is the responsibility of manufacturers and retailers, and CSR is the responsibility of manufacturers. Numerical examples are provided to verify the effectiveness of the model and analyzed to describe how marketing and CSR affect equilibrium results. We find that the retailers are responsible for marketing, and the level of CSR activities of the manufacturers is higher during the early period, which is most beneficial to the multi-period CLSCN system and social welfare. Based on the conclusions of this paper, the management enlightenments from the perspectives of enterprises and government are also proposed.

As is the case in many big data mining scenarios with a large scale of samples, the heavy computation cost hinders the application of machine learning, which has to iteratively compute by passing over the whole dataset without considering the roles of different samples in training computation. However, we argue that most of the samples dominating computation resources contribute little to the gradient-based model update, particularly when the model is close to convergence. We define this observation as the Sample Contribution Pattern (SCP) in machine learning. This paper proposes two approaches to exploit SCP by detecting gradient characteristics and triggering the reuse of outdated gradients. In particular, this paper reports research results in (1) the definition and description of SCP to reveal an intrinsic gradient contribution pattern of different samples; (2) a novel SCP-based optimizing algorithm (SCPOA) that outperforms alternative tested algorithms in terms of computation overhead; (3) a variant of SCPOA that incorporates discarding-recovering mechanisms to carefully tradeoff between model accuracy and computation cost; (4) the implementation and evaluation of two algorithms based on popular distributed big data mining platforms running typical sample-sets; (5) intuitive convergence proof of the algorithms. Our experimental results illustrate that the proposed approaches can significantly reduce the computation cost with competitive accuracy.

The widespread use of Unmanned Aerial Vehicles (UAV) has made the security and computing resource application efficiency of UAV a hot topic in the security field of the Internet of Things. In this paper, an optimized lightweight identity security authentication protocol, Optimized Identity Authentication Protocol (ODIAP) is proposed for Internet of Drones (IoD) networks. The protocol is targeted to the security risks faced by IoD networks, and proposes the security authentication mechanism consisting of 3 phases and 7 authentication processes, which enables the protocol has both forward and backward security, and can resist mainstream network attacks. Meanwhile, this paper fully considers the computational load and proposes the identity information generation and verification method based on the Chinese residual theorem, which reduces the computational load of resource-constrained nodes and shifts the complex computational process to server nodes with abundant computational resources. Moreover, after security protocol analysis and tool verification based on the automated security verification tool Proverif, the protocol in this paper has complete security. At the same time, the performance analysis and comparison with other mainstream protocols shows that this protocol effectively optimizes the use of computing resources without compromising security.

In recent years, a variety of supervised manifold learning techniques have been proposed to outperform their unsupervised alternative versions in terms of classification accuracy and data structure capturing. Some dissimilarity measures have been used in these techniques to guide the dimensionality reduction process. Their good performance was empirically demonstrated; however, the relevant analysis is still missing. This paper contributes to a theoretical analysis on a) how dissimilarity measures affect maintaining manifold neighbourhood structure and b) how supervised manifold learning techniques could contribute to the reduction of classification error. This paper also provides a cross-comparison between supervised and unsupervised manifold learning approaches in terms of structure capturing using Kendall’s Tau coefficients and co-ranking matrices. Four different metrics (including three dissimilarity measures and Euclidean distance) have been considered along with manifold learning methods such as Isomap, ${t}$ -Stochastic Neighbour Embedding ( ${t}$ -SNE), and Laplacian Eigenmaps (LE), in two datasets: Breast Cancer and Swiss-Roll. This paper concludes that although the dissimilarity measures used in the manifold learning techniques can reduce classification error, they do not learn well or preserve the structure of the hidden manifold in the high dimensional space, but instead, they destroy the structure of the data. Based on the findings of this paper, it is advisable to use supervised manifold learning techniques as a pre-processing step in classification. In addition, it is not advisable to apply supervised manifold learning for visualization purposes since the two-dimensional representation using supervised manifold learning does not improve the preservation of data structure.

Proton CT (pCT) is a promising new imaging technique that can reconstruct relative stopping power (RSP) more accurately than x-ray CT in each cubic millimeter voxel of the patient. This, in turn, will result in better proton range accuracy and, therefore, smaller planned tumor volumes (PTV). The hardware description and some reconstructed images have previously been reported. In a series of two contributions, we focus on presenting the software algorithms that convert pCT detector data to the final reconstructed pCT images for application in proton treatment planning. There were several options on how to accomplish this, and we will describe our solutions at each stage of the data processing chain. In the first paper of this series, we present the data acquisition with the pCT tracking and energy-range detectors and how the data are preprocessed, including the conversion to the well-formatted track information from tracking data and water-equivalent path length from the data of a calibrated multi-stage energy-range detector. These preprocessed data are then used for the initial image formation with an FDK cone-beam CT algorithm. The output of data acquisition, preprocessing, and FDK reconstruction is presented along with illustrative imaging results for two phantoms, including a pediatric head phantom. The second paper in this series will demonstrate the use of iterative solvers in conjunction with the superiorization methodology to further improve the images resulting from the upfront FDK image reconstruction and the implementation of these algorithms on a hybrid CPU/GPU computer cluster.

This paper proposes a novel method that uses stator current signals to detect motor faults under operational speed and load torque conditions. Previous studies on motor current signature analysis (MCSA) have been devoted to developing methods to detect faults in non-stationary conditions; however, they have limitations. Conventional methods require much domain knowledge or parameter selection for signal decomposition, and are applicable under limited variable conditions. Thus, this paper proposes a new feature, drive-tolerant current residual variance (DTCRV), for fault detection. This new approach requires no domain knowledge and is applicable under varying speed and load torque conditions. In the proposed method, first, the envelope of the current signal is calculated to extract its modulation. Second, the drive-related signal, which greatly varies based on speed and load torque conditions, is extracted from the enveloped current signal. Third, the drive-tolerant current residual (DTCR) is calculated; the DTCR is defined as the subtraction of the drive-related signal from the enveloped current signal. Finally, the new health feature is calculated as the variance of the DTCR. To demonstrate the proposed method, experimental studies were conducted under several operating conditions (i.e., different speed profiles and load torque levels) with two fault modes: 1) a stator inter-turn short and 2) misalignment. Results confirm the ability of DTCRV to promptly and accurately detect faults in a variety of conditions; in contrast, conventional methods are greatly affected by the operating conditions.

In the literature of Economics, Engineering and Operations Research, the estimation of production frontiers is a current hot topic. Many parametric and nonparametric methodologies have been introduced for estimating technical efficiency of a set of units (for example, firms) from the production frontier. However, few of these methodologies are based upon machine learning techniques, despite being a rising field of research. Recently, a bridge has been built between these literatures, machine learning and production theory, through a new technique proposed in Esteve et al. (2020), called Efficiency Analysis Trees (EAT). The algorithm developed from EAT, based on the well-known Classification and Regression Trees (CART) machine learning technique, is a greedy technique that uses a particular heuristic for the selection of the next node to be split during the decision tree development process. Nevertheless, as we show in this paper, for different sample sizes and number of variables, the heuristic used by EAT is not capable of obtaining the tree with the minimum mean square error (MSE). For this reason, in this paper, a backtracking technique is implemented to improve the MSE obtained by the EAT algorithm. Additionally, a pair of new algorithms are introduced which combine the heuristic technique used by the standard EAT and the backtracking algorithm to enhance the reduction of the MSE, while decreasing the computation time. Our research is based on some simulated experiments. According to our computational results, the combination of the heuristic and the backtracking algorithm, in particular, that in which the tree growth starts with heuristics and ends with backtracking, has achieved an accuracy similar to that of backtracking and within a reasonable computational time. The contribution of the paper could be of special interest for industrial engineers interested in measuring efficiency and productivity of industrial processes in many sectors, such as energy, agri-food or service industries.

This paper considers the problem of expanding a language class that can be proven by a non-interactive zero-knowledge proof system (NIZK) in a black-box manner in the common reference string model. Namely, given NIZKs for two languages, ${\mathcal L}_{0}$ and ${\mathcal L}_{1}$ , can we construct an NIZK for ${\mathcal L}_{0} \vee {\mathcal L} _{1}$ in a black-box manner? NIZKs for disjunctive languages have a large number of applications, such as electronic voting. Therefore, such a black-box construction may enable the efficient constructions of such applications. However, Abe et al. (PKC 2020) showed that this is impossible if the two given NIZKs are simulation-sound. In this paper, we prove that it is also impossible if the two given NIZKs are constructed by the commit-and-prove methodology that is typically used in many cryptographic protocols, including NIZKs. This result suggests that if we want to augment the capability of NIZKs in terms of the languages they can prove, we should rely on certain properties or structures of the underlying NIZKs, such as algebraic structures.

In this paper, a color image encryption algorithm based on the fractional-order multi-scroll Chen chaotic system and DNA mutation principle is proposed. The dynamical performances of the fractional-order multi-scroll Chen chaotic system are analyzed by phase diagram, Lyapunov exponential spectrum and bifurcation diagram. Meanwhile, we realized the hardware circuit simulation of the chaotic system on the DSP platform. Based on comprehensive analysis, an image encryption algorithm is designed. In particular, a DNA algorithm with mutation effect has been introduced into the encryption algorithm. Finally, the performances of the designed encryption scheme are analyzed by key space, correlation coefficients, information entropy, histogram, differential attacks and robustness analysis. The experimental results prove that the algorithm has strong encryption capabilities and can withstand multiple decryption methods. The new color image encryption scheme proposed in this paper can realize the secure communication of digital images.

This paper has the purpose to investigate HVDC insulation design considering real operating conditions, when DC steady-state is affected by frequent voltage transients or load variations that may be present during all life. Electrical field distribution in insulation, and in insulation defects, may change significantly from DC steady-state when voltage and load vary with time, which can cause partial discharge activity often not been properly accounted for at the design stage. The Part I of this paper is dedicated to prove, through experiments, models and simulations, that electrical and thermal transients may incept partial discharges in defective insulations during cable energization, voltage polarity inversion at a constant nominal load, as well as during load variations at a constant nominal voltage. This can cause accelerated aging and premature breakdown even if the insulation system is designed properly to withstand DC electrothermal stress, without partial discharges in steady state, for all life, as it will be shown in Part II. Focus is on cables, but the approach described here is general for any DC insulation system.

Due to it is difficulty to segment the steel bar image in a complex background and with external interference. In this paper, we propose a multi-attention U-Net to segment the steel bar image. First of all, in order to accurately find the steel bar region and filter the noise in the background part, we add the row mean attention module in the decoding path of the U-shaped network by using the characteristic of the constant diameter of the steel bar, which reduces the background to be segmented into steel bar. In addition, an attention branch optimization strategy based on mask attention module is designed, which uses the output of high-level semantics to filter the features of adjacent low-level semantics, which can maintain the continuity of the segmented steel bar region. Secondly, we design an improved loss function for training, which can improve the accuracy of fitting of steel bar width and better optimize the effect of steel bar segmentation. Finally, in order to improve the generalization ability of the multi-attention U-Net method and avoid over fitting, we propose a data augmentation method based on correction deformation to expand the sample database. Compared with standard U-Net, attention U-Net, R2U-Net and DUNet, the experimental results show that the multi-attention U-Net proposed in this paper has higher IoU accuracy in steel bar image segmentation, and this method has real-time performance.

This paper presents the development of an easy-to-deploy and smart monitoring IoT system that utilizes vibration measurement devices to assess real-time condition of bulldozers, power shovels and backhoes, in non-stationary operations in the mining industry. According to operating experience data and the type of mining machine, total loss failure rates per machine fleet can reach up to 30%. Vibration analysis techniques are commonly used for condition monitoring and early detection of unforeseen failures to generate predictive maintenance plans for heavy machinery. However, this maintenance strategy is intensively used only for stationary machines and/or mobile machinery in stationary operations. Today, there is a lack of proper solutions to detect and prevent critical failures for non-stationary machinery. This paper shows a cost-effective solution proposal for implementing a vibration sensor network with wireless communication and machine learning data-driven capabilities for condition monitoring of non-stationary heavy machinery in mining operations. During the machine operation, 3-axis accelerations were measured using two sensors deployed across the machine. The machine accelerations (amplitudes and frequencies) are measured in two different frequency spectrums to improve each sensing location's time resolution. Multiple machine learning algorithms use this machine data to assess conditions according to manufacturer recommendations and operational benchmarks Proposed data-driven machine learning models classify the machine condition in states according to the ISO 2372 standards for vibration severity: Good, Acceptable, Unsatisfactory, or Unacceptable. After performing field tests with bulldozers and backhoes from different manufacturers, the machine learning algorithms are able to classify machine health status with an accuracy between 85% - 95%. Moreover, the system allows early detection of “Unacceptable” states between 120 to 170 hours prior to critical failure. These results demonstrate that the proposed system will collect relevant data to generate predictive maintenance plans and avoid unplanned downtimes.

It is expected that peer to peer energy trading will constitute a significant share of research in upcoming generation power systems due to the rising demand of energy in smart microgrids. However, the on-demand use of energy is considered a big challenge to achieve the optimal cost for households. This paper proposes a blockchain-based predictive energy trading platform to provide real-time support, day-ahead controlling, and generation scheduling of distributed energy resources. The proposed blockchain-based platform consists of two modules; blockchain-based energy trading and smart contract enabled predictive analytics modules. The blockchain module allows peers with real-time energy consumption monitoring, easy energy trading control, reward model, and unchangeable energy trading transaction logs. The smart contract enabled predictive analytics module aims to build a prediction model based on historical energy consumption data to predict short-term energy consumption. This paper uses real energy consumption data acquired from the Jeju province energy department, the Republic of Korea. This study aims to achieve optimal power flow and energy crowdsourcing, supporting energy trading among the consumer and prosumer. Energy trading is based on day-ahead, real-time control, and scheduling of distributed energy resources to meet the smart grid’s load demand. Moreover, we use data mining techniques to perform time-series analysis to extract and analyze underlying patterns from the historical energy consumption data. The time-series analysis supports energy management to devise better future decisions to plan and manage energy resources effectively. To evaluate the proposed predictive model’s performance, we have used several statistical measures, such as mean square error and root mean square error on various machine learning models, namely recurrent neural networks and alike. Moreover, we also evaluate the blockchain platform’s effectiveness through hyperledger calliper in terms of latency, throughput, and resource utilization. Based on the experimental results, the proposed model is effectively used for energy crowdsourcing between the prosumer and consumer to attain service quality.

Due to the lack of inertial support of the physical rotor of reliable power, the problem of weak inertia of the system is prominent when large-scale grid connection. Aiming at the weak inertia problem of new energy power systems, this paper takes the photovoltaic power generation system with generalized droop control as the research object. Firstly, the paper introduces the structure of the photovoltaic power generation system and the mathematical principle of generalized droop control At the same time, the electrical torque model of the system is established in order to reveal the inertia characteristics of the grid-tied inverter under the generalized droop control, moreover, the influencing factors of the system’s inertia characteristics and the influence rules of parameters are analyzed and studied. Finally, simulation analysis verifies the correctness of the analysis. The research results show that the photovoltaic inverter system under the generalized droop control has obvious inertia characteristics, the change of inertia size is affected by the dominant zero pole of the controller, and the equivalent inertia coefficient has frequency domain characteristics.

To reduce waste and cost as well as to promote the efficient and sustainable use of resources in supply chains, a common focus of practice and research is to integrate decisions of various operational processes such as production, inventory, distribution, and routing. The question of which is more representative of the production routing problem (PRP) then arises. In this paper, the focus is on uncertainty in the PRP, and demand and cost uncertainty are considered simultaneously. According to different decision criteria, three uncertain programming models are correspondingly formulated. Then, through researching the crisp equivalence and conversion of the proposed uncertain models, a series of crisp equivalent models are proposed under the assumptions of particular uncertainty distributions, such as linear, zigzag, and normal distributions. To verify the accuracy and usefulness of the proposed models put forward in this paper, a series of experiments are conducted. Finally, several interesting managerial aspects with respect to the relationship between the confidence level and variance of uncertain variables that are gained from the numerical experiments are highlighted. First, the overall cost of PRP grows as the confidence level increases under uncertain environment. Second, the probability that the optimal total cost of the PRP is less than or equal to a given threshold strictly increases as the threshold increases under uncertain environment. Third, in circumstances such as higher confidence level that decision makers generally pay more attention to, the growth of the variance of uncertain variables may lead to the increase of the total cost.

The Bernoulli filter is a general, Bayes-optimal solution for tracking a single disappearing and reappearing target, using a single sensor whose observations are corrupted by missed detections and a general, known clutter process. Like virtually all target-tracking algorithms it presumes a hidden Markov model (HMM) structure on the sensor and target. Pieczynski's pairwise Markov model (PMM) relaxes this assumption, thereby addressing correlated sensor noise and non-Markovian target motion. In an earlier paper, we derived a “PMM Bernoulli filter” that obeys PMM rather than restrictive HMM sensor/target statistics. This paper generalizes both the HMM and PMM Bernoulli filters to the case of multiple, possibly correlated sensors, resulting in a general, Bayes-optimal single-target tracker for complexly correlated sensors.

Compared with silicon (Si) IGBTs, silicon carbide (SiC) MOSFETs have much faster switching speeds and high switching frequency operation capability, enabling compact and high-efficiency motor drive systems. However, the increased switching speed and frequency also cause increased-level of common-mode (CM) voltage with higher slew rates (dv/dt). The CM voltage leads to machine leakage currents as well as bearing currents such as electric discharge machining (EDM) type current and capacitive-type (dv/dt) current. These bearing currents can cause degradation or failure of motor bearings. In order to investigate the impact of SiC motor drives on the motor bearing currents, in this paper, the mechanism and modelling of bearing currents are analyzed first. Then, a direct measurement method is used to assess the bearing currents in the induction motor driven by the SiC converter. In the experiment, the number of EDM current events is counted and the amplitude of the capacitive-type of current is also examined under various switching speeds and frequencies of SiC devices. Furthermore, the bearing currents are also extensively tested under various bearing temperatures, motor speeds and dc-link voltages. The correlations between the bearing currents and various factors have been revealed in this paper.

The epidemic increase in online reviews’ growth made the sentiment classification a fascinating domain in academic and industrial research. The reviews assist several domains, which is complicated to gather annotated training data. Several sentiment classification methodologies are devised for performing the sentiment analysis, but retrieval of information is not accurately performed, less effective, and less convergence speed. In this paper, we propose a sentiment paper proposes a sentiment classification model, namely Spider Monkey Crow Optimization algorithm (SMCA), for training the deep recurrent neural network (DeepRNN). In this method, the telecom review is employed to remove stop words and stemming to eliminate inappropriate data to minimize user’s seeking time. Meanwhile, the feature extraction is performed using SentiWordNet to derive the sentiments from the reviews. The extracted SentiWordNet features and other features, like elongated words, punctuation, hashtag, and numerical values, are employed in the DeepRNN for classifying sentiments. To retrieve the required review, the Fuzzy K-Nearest neighbor (Fuzzy-KNN) is employed to retrieve the review based on a distance measure. With rigorous assessments and experimentation, it is observed that the proposed SMCA-based DeepRNN performs better in terms of accuracy of 97.7%, precision of 95.5%, recall of 94.6%, and F1-score 96.7%, respectively.

Due to the limitations of welding complexity and machining error, traditional manual teaching and offline programming are not intelligent enough and have weak adaptability to workpiece. At present, the 2D perception visual welding guidance programming method is commonly used which cannot accurately locate and model the complicated 3D spatial curve welding seam. The 2D perception method can hardly meet the requirements of welding process. In this paper, a welding seam perception method based on a line structure-light sensor was proposed, which optimizes the generation of the weld seam trajectory, and builds a highly adaptable intelligent guidance programming system for welding robots. Firstly, 3D modeling perception of welding parts is realized through eye-in-hand system of robot, which solves the problem that offline programming system cannot be applied when the welding model is not precise enough or partly miss. Secondly, aiming at solving extraction problem of common types of 3D space curve welding seam, corresponding types of weld extraction algorithms are proposed according to the characteristics of different types of welds under the general process of weld extraction. These methods not only can directly extract the weld from the ordered point cloud with high precision and resolution, but also are less affected by the welding environment, which solve the problem of low perception accuracy of complex curved welds in 3D space. Then, on the basis of welding seam extraction, NURBS curves are used to realize the optimal generation of weld trajectory. Finally, the feasibility and effectiveness of all the methods proposed in this paper are verified by a large number of experiments.

The coupling of communication networks plays an indispensable role in modern power systems; however, it also leads to many problems due to cascading failure. Although most current research focuses on the single-layer, non-interacting system and physical layer network, few studies have combined the complex network theory to ignore the influence of communication networks. To address this problem, this paper introduces a cascading failure model of a cyber physical power system (CPPS) that considers the operation characteristics of the communication layer, especially the influence of transmission delay and connectivity on stability control. First, the influence mode of the communication layer failure node acting on the physical layer is analyzed, and the interaction mechanism between the communication layer and physical layer is clarified. Furthermore, the propagation process of failure in the CPPS system is modeled, and the influence of information transmission delay on the stability control process is considered. In this manner, the development process of cascading failure in a CPPS system is described accurately. Finally, according to the loss rate of the physical layer load, the influence of the communication layer node is evaluated to verify the accuracy of the model. This paper also provides a practical model of a CPPS system, which is helpful for building a secure and reliable energy Internet.

Timing synchronization has a vital role in swarm drones’ network (SDN) or a swarm of unmanned aerial vehicle (UAV) network. Current timing synchronization methods focus on enhancing single-hop skews which remarkably improve timing synchronization precision at this level. The improper clock of the drone system can cause interference, affect spectrum precision and interrupt the operation of the transceiver. In the drones’ network, master drones’ (MD) neighbor drone’s timing synchronization approaches like Reference Broadcast System (RBS) realize a good performance. However, the requirement of one super drone with a large number of broadcasts for RBS makes it unrealistic to use in some situations like SDN network situation. Appropriate study and adjustments are needed to have real timing synchronization by eliminating the clocks drift and enhancing the timing synchronization precision. Therefore, a new self-timing synchronization approach is proposed in this paper where several MD drones can autonomously generate swarm clusters. The cluster head (CH) instigates a timing synchronization procedure starting with intra-Swarm cluster timing synchronization. The intermediate drones (ID) are elected between two swarm clusters to synchronize all drones in line with the inter-swarm cluster timing synchronization approach. The proposed approach is distributed and flexible to achieve high timing synchronization precision. The paper proposes a novel self-timing synchronization approach for in large scale semi-flat SND network architecture. Self-timing synchronization is swarm cluster-based and applicable for a huge number of master drones in SDN. One is the intra-Swarm cluster where the timing synchronization procedure starts with the CH to synchronize all CM. Secondly, in the inter-swarm cluster timing synchronization, two clusters are synchronized via intermediate drone (ID). However, the simulations demonstrated that in many cases all CHs are synchronized by the synchronized CHs from intra-swarm cluster timing synchronizations; this increased the system throughput and synchronization delay to about 75% compared to what we planned to achieve. Moreover, the simulation results also proved that the achieved synchronization precision can be used for position estimation and prediction with high accuracy.

This paper presents a complete procedure on prototyping using the FPGA of the STEMlab board and is intended to serve as a guide for developers, students and researchers interested in speeding up their projects and experiments. Due to the reconfigurability of its internal circuitry, being as simple as a code modification (using hardware description language), FPGA technology allows testing of several controller topologies and/or parameters without the need of any physical change at hardware. This feature allows a much faster development cycle of either commercial products or academic experiments. Besides the reconfigurability of the FPGA, the STEMlab board also offers the advantage of several peripheral already available, which includes, among others, high speed analog-to-digital and digital-to-analog converters, Ethernet communication and a dual-core ARM processor capable of running a Linux operating system. In this paper, a didactic method of use of this board is presented, from getting started to a complete academic and industrial application: detection of early damage on an induction motor using frequency response analysis.

Accident causal scenario can describe the process logic of the accident clearly and concretely from the perspective of the control mechanism. Only by improving the quality of the causal scenario can the effective control measures be taken. Combining the technical characteristics of the fully automatic operation (FAO) system, the paper proposes an automated accident causal scenario identification method for FAO system based on the System-Theoretic Process Analysis (STPA) method. Aiming at the problem that there are too many layers in the hierarchical control structure diagram of STPA method, which makes it impossible to effectively trace the cause and the problem that the basic control structure model only contains the control structural information and lacks the cause information, a new basic control structure model is defined to model multiple control processes in time sequence, and then the paper extends it from four aspects: control action, input variables, external disturbance, and synchronous timing to add more system cause information. For the lack of a unified standard description problem for the causal scenario, a four-stage causal scenario description method is defined, this paper has developed the first timing, non-first timing, synchronous timing, and external disturbance causal scenario search rules to ensure the automatic identification of the causal scenarios. Applying the automated safety analysis method to the case study of the operational scenarios of parking in a station of Beijing Yanfang Line, the automated identification of related causal scenarios is successfully completed through the Auto-STPA platform, and corresponding safety requirements are added. The feasibility of the method and the applicability to the analysis of operational scenarios are verified.

Outlier detection is an important task in the field of big data analysis. The technology has been extensively used in network security, sensor data analysis, public health and so on. In an outlier detection system, with the continuous expansion of upper-layer applications, a system needs to process a large number of query requests in a very short time, which places high requirements on the timeliness of outlier detection algorithms. To solve this problem, in this paper, an efficient algorithm, R-tree based Outlier Detection Algorithm (RODA), is proposed, which can effectively support single query and multiple query processing. For single query processing, we first extended the R-tree index and proposed a new outlier estimation method. Using the techniques above, the algorithm greatly reduces the retrieval space by preferentially scanning data points with high outlier-degrees. For multiple query processing, the algorithm deeply analyzes the sharing mechanism between multiple queries in order to handle multiple detection tasks within one processing. Finally, experiment results show that the RODA proposed in this paper has improved operating efficiency, and has good applicability and practical significance.

In this paper, an extensive reliability analysis of wind energy conversion systems (WECS) is presented. Elaborate the analysis is presented starting from the subassembly level to the subsystem level, then the system or the overall WECS. The fault tree method with a Weibull probability distribution function is introduced as a complete model for estimating the wind turbine subassemblies’ reliability. The model was tested using a massive dataset of failure rates of various wind turbine subassemblies derived from relevant literature, comprising various operating concepts and the different climate conditions. In addition, ranking for various subassemblies of wind energy conversion systems concerning their impact on the overall system reliability is also presented in this paper to identify the weak items and subsystems. This identification guides the designers and planners in setting the appropriate maintenance strategies to increase the overall reliability of the considered systems and achieve a desired level of reliability. The results indicate that the model has practical applications for managing wind turbines, and the implementation demonstrates the proposed approach’s effectiveness and efficiency, which may significantly enhance the WECS reliability.

Circuit breaker (CB) and fault current limiter (FCL) are two major fault protection devices used in mesh-type DC microgrids. This paper proposes the parameters selection method to obtain a reliable and economic configuration scheme of CBs and FCLs applied in mesh-type DC microgrid. The breaking time of CB, the nominal breaking current of CB and the inductance of FCL are selected as three optimization parameters in an evaluation model. Since the reliability of fault protection scheme depends on whether the nominal breaking current of the CB is greater than the line current at the breaking moment of CB, it is necessary to accurately calculate the post-fault line current. Based on this, an accurate transient DC microgrid model is presented in this paper. And then, an improved non-dominated sorting genetic algorithm II (NSGA-II) is used to configure the parameters of CBs and FCLs quickly. Besides, a case study on six-terminal DC microgrid test system shows that the proposed method can obtain accurate post-fault line current and can achieve the parameters selection of CBs and FCLs.

Due to the high dependence of economic and social development on power systems, the demand for reliable operation of power systems is increasing. Considering the popularity and widespread installation of smart meters, accurate system/node reliability indexes can be obtained. The inverse problem of reliability evaluation (IPRE) refers to the use of known system/node reliability indexes to obtain component reliability parameters. In this paper, a novel method of solving the IPRE is proposed. First, based on a nonsequential Monte Carlo (NSMC) method, analytical expressions for system reliability indexes in terms of component reliability parameters are derived, and then, the nonlinear equations of the IPRE are constructed. Second, a high-order polynomial approximation based on the conjugate gradient algorithm is used to calculate the unknown component reliability parameters, and the results are compared with those obtained using traditional neural networks method. Finally, a continuation method is used to correct the errors of the obtained component reliability parameters. Three cases, namely, the IEEE 1979 Reliability Test System (IEEE RTS-79), the Roy Billinton Test System (RBTS) and the Chuanyu power system in Southwest China, are used to test the method proposed in this paper to verify its feasibility and accuracy.

Emergency rescue vehicles are special equipment for fire, flood, earthquake and other disasters. They need to have high efficiency and high mobility under various terrain and road conditions. The fuel economy of emergency rescue vehicles is very poor in climbing and complex terrain due to the heavy weight of vehicle chassis and upper loading. The dual-motor torque increasing hybrid power system designed in this paper greatly improves the dynamic performance and mobility of emergency rescue vehicles, and the use of dual-motor drive in steep slopes and complex terrain can avoid the engine working in low efficiency area. In order to further improve the fuel economy of vehicles under various working conditions, a fuzzy logic control strategy based on improved particle swarm optimization (PSO) is proposed in this paper. The torques of engine and dual-motor are reasonably distributed under different working conditions. A novel fuzzy parameter optimization mode is designed, which reduces the workload of optimization calculation and ensures the optimization accuracy. The off-line simulation and hardware-in-the-loop experiments are carried out for the dual-motor torque increasing hybrid power system model and the proposed improved energy control strategy. The results show that the fuzzy logic control strategy optimized by simulated annealing particle swarm optimization algorithm (SimuAPSO-FLC) has the best effect and meets the requirements of high efficiency, high mobility and stability of the emergency rescue vehicle.

The paper proposes a novel interleaved AC-DC ZCS-PWM boost converter that requires the use of just a single active auxiliary switch to assist in the turning off the main power circuit switches with ZCS. The auxiliary switch can be turned on and off with ZCS and its auxiliary circuit allows the converter to operate without an increase in the main switch peak current or voltage stress. The auxiliary switch in the converter is active for a much shorter time than in most other ZCS-PWM converter, which allows the converter to operate at higher power levels than other previously proposed interleaved ZCS-PWM converter with a single auxiliary switch. The proposed converter’s operation is explained in the paper and its key features and design considerations are discussed. Experimental results that confirm the operation of the proposed converter are presented as well.

Knowledge distillation (KD) is one of the most effective neural network light-weighting techniques when training data is available. However, KD is seldom applicable to an environment where it is difficult or impossible to access training data. To solve this problem, a complete zero-shot KD (C-ZSKD) based on adversarial learning has been recently proposed, but the so-called biased sample generation problem limits the performance of C-ZSKD. To overcome this limitation, this paper proposes a novel C-ZSKD algorithm that utilizes a label-free adversarial perturbation. The proposed adversarial perturbation derives a constraint of the squared norm of gradient style by using the convolution of probability distributions and the 2nd order Taylor series approximation. The constraint serves to increase the variance of the adversarial sample distribution, which makes the student model learn the decision boundary of the teacher model more accurately without labeled data. Through analysis of the distribution of adversarial samples on the embedded space, this paper also provides an insight into the characteristics of adversarial samples that are effective for adversarial learning-based C-ZSKD.

The main purpose of this paper is to achieve ultra-low power Physical Unclonable Function (PUF) to meet the requirements for Internet of Things (IoT) applications. PUFs are promising hardware security primitives that are based on the uniqueness and the unclonability of the device's physical characteristics to provide a unique identifier for devices. PUFs can be used in device authentication and for secure key storage and generation. This paper presents Oscillator Collapse Physical Unclonable Function (OC-PUF), which is suitable for low power applications. The power consumption is reduced based on designing the most power-hungry modules in the OC-PUF. An Oscillator Collapse (OC) is designed to work in the near-threshold voltage region, which reduces the power consumption. More power reduction is achieved by designing a new Collapse Time Comparator (CTC). Due to the process variations, the oscillations period of each OC is different. The CTC generates the output response bit by comparing the oscillations periods of the two selected OCs. The simulation results demonstrate that the proposed OC-PUF can effectively reduce the power consumption. The proposed PUF is designed using 20 nm triple gate FinFET technology. The Simulation results for 1000 different chips with the same input challenge, show that the average power is 140 nW, with the worst case being 740 nW. The best case is 63 nW per challenge-response pair at supply voltage 0.5 V. The averaged reliability of the OC-PUF is 99.8%, at temperatures from -40 to 125 °C and supply voltage 0.5 ± 10%. The proposed OC-PUF decreases the power consumption while retaining high-performance metrics.

As an emerging field of information technology, the Internet of Health Things has attracted great attention from governments, scholars, and related enterprises, and is seen as a major opportunity for development and change in the information field. The European Commission believes that the development and application of the Internet of Health Things will make a significant contribution to solving modern social problems in the next 5 to 15 years. In this paper, the corresponding motion detection algorithms such as pacing detection algorithm, sleep quality and sedentary reminder detection algorithm are designed for real-time detection of motion status. In addition, this paper builds a new safety architecture model based on real-time motion detection, and proposes a time-domain feature-based motion detection method for walking, walking upstairs and walking downstairs. The original acceleration signal is smoothed and denoised using a sliding-average filter. The acceleration signal is segmented by a rectangular window with 50% overlap, and the variance, X-quartile difference, and X-axis bias coefficient are extracted from a single time window.

Grasshopper Optimization Algorithm (GOA) is a recent swarm intelligence algorithm inspired by the foraging and swarming behavior of grasshoppers in nature. The GOA algorithm has been successfully applied to solve various optimization problems in several domains and demonstrated its merits in the literature. This paper proposes a comprehensive review of GOA based on more than 120 scientific articles published by leading publishers: IEEE, Springer, Elsevier, IET, Hindawi, and others. It provides the GOA variants, including multi-objective and hybrid variants. It also discusses the main applications of GOA in various fields such as scheduling, economic dispatch, feature selection, load frequency control, distributed generation, wind energy system, and other engineering problems. Finally, the paper provides some possible future research directions in this area.

Hyperspectral and multispectral information processing systems and technologies have demonstrated its usefulness for the improvement of agricultural productivity and practices by providing useful information to farmers and crop managers on the factors affecting crop status and growth. These technologies are widely used in a range of agriculture applications such as crop management, crop yield forecasting, crop disease detection, and the monitoring of agriculture land usage, water, and soil conditions. Hyperspectral information sensing can acquire several hundred spectral bands that cover the electromagnetic spectrum of an observational scene in a single acquisition. The resulting hyperspectral data cube contains a large volume of spatial and spectral information. The hyperspectral sequence of images or video further increases the data generation velocity and volume which lead to the Big data challenges particularly in agricultural remote sensing applications. This paper is structured to first give a comprehensive review of representative studies to provide insights into significant research efforts in agriculture using Big data, machine learning and deep learning with the focus on frameworks or architectures, information processing and analytics with hyperspectral and multispectral data. The potential for utilizing Big data, machine learning and deep learning for hyperspectral and multispectral data in agriculture is very promising. The paper then further explores the potential of using ensemble machine learning and scalable parallel discriminant analysis which takes into consideration the spatial and spectral components for Big data in agriculture. To the best of our knowledge, no similar review study on agriculture with Big data, machine learning and deep learning for hyperspectral and multispectral information processing has been reported. Furthermore, the potential of ensemble machine learning and scalable parallel discriminant analysis has not been explored in agriculture information processing. Experiments and data analytics have been performed on hyperspectral data from agriculture for validation. The results have shown the good performance of our approach.

In this paper, a finite control set model predictive direct power control (FCS-MPDPC) method based on satisfactory optimization, for single-phase three-level PWM rectifier, is proposed to achieve global optimization that takes into account all its objectives and constraints. Satisfaction optimization aims to obtain the satisfactory solution after coordination of multiple goals, instead of the optimal solution of a single goal. By replacing “optimal” with “satisfaction”, more control degrees of freedom are acquired, so that low-priority auxiliary control objectives can participate in the optimization process. Meanwhile, in order to enhance the description accuracy of FCS-MPDPC method for the future trend of PWM rectifier, the prediction time domain is extended from the traditional single-step to multi-step, and the average switching frequency model is established to realize the low switching frequency control. The satisfactory optimized FCS-MPDPC method proposed in this paper is compared, through simulation and experimental results, with the standard FCS-MPDPC method, which verifies the effectiveness and superiority of the proposed algorithm.