Search

Frequency spatial distribution characteristics of interconnected power systems are highlighted, resulting in significant regional frequency differences and inter-region tie-line power fluctuations, posing a threat to frequency security operation. For two-region interconnected power systems, analytical expressions for regional frequency and inter-regional tie-line power are derived based on the low-order frequency response model. By dividing the fast-varying part and the slow-varying part of the above analytical expressions, analytical frequency security indicators including nadir value, quasi-steady-state value, maximum rate value of regional frequency, and peak value, quasi-steady-state value of inter-regional tie-line power are derived. By dividing the fast-varying part and slow-varying part of the aforementioned analytical expressions, we further derived analytical frequency security indicators, including nadir value, quasi-steady-state value, maximum rate value of regional frequency, and peak value, quasi-steady-state value of inter-area tie-line power. Through case studies based on the IEEE 2-region 4-machine system, the results indicate that the obtained analytical frequency security indicators can accurately describe the frequency dynamics following a major disturbance for two-region interconnected power systems.

Lane detection is fundamental to autonomous driving, yet remains challenging in complex environments with occlusions, ambiguous markings, and varied lighting. We introduce the Global Semantic Enhancement Network (GSENet), a groundbreaking framework that significantly advances lane detection accuracy and robustness. GSENet’s core innovations include the Global feature Extraction Module (GEM) and the Top Layer Auxiliary Module (TLAM). GEM revolutionizes the extraction of fine-grained global features, overcoming limitations of traditional deep convolutional approaches without compromising inference speed. TLAM leverages self-attention mechanisms to capture rich contextual information and learn task-specific representations, dramatically enhancing the network’s performance in complex scenarios. We further propose the Generalized Line Intersection over Union (GLIoU) Loss, a novel optimization approach that considers spatial relationships between lane points and introduces a geometric penalty term. This loss function promotes globally coherent and smooth lane predictions, addressing key limitations in existing methods. Our comprehensive mathematical analyses, including gradient derivations and complexity assessments, provide theoretical foundations for the effectiveness of these innovations. Extensive experiments on challenging benchmarks demonstrate GSENet’s superior accuracy and robustness, significantly outperforming state-of-the-art methods. Notably, our framework’s modular design extends its applicability beyond lane detection to various computer vision tasks involving elongated or curved structures, opening new avenues for research and practical applications in autonomous systems and beyond.

The normal operation of insulator strings affects the safety and stability of the power system, and insulator string flashover is one of the important faults. In this paper, considering the flashover characteristics of insulator strings in complex environments, noise is added to the collected insulator strings to simulate the actual complex environment, and then the collected data are rotationally transformed and filtered using an improved non-local mean filtering algorithm. To accurately locate insulator strings in complex environments, the geodesic active contour correction algorithm is employed to locate and segment the image. This algorithm is developed based on the level set model, replaces the image target boundary finding problem with the problem of solving a weighted arc length minimum, and introduces a penalty term into the level set energy generalization that constrains the distance function of the level set, which effectively solves the edge leakage problem. For the segmented image of insulator strings, grayscale features and wavelet features are extracted, and then the optimized random forest algorithm is utilized for prediction analysis, and the diversity of weak learners in the random forest algorithm is increased not only through sample perturbation but also through attribute perturbation, leading to excellent generalization performance. Additionally, by combining the misclassification matrix and the a priori probability optimization algorithm, the random forest algorithm is optimized to achieve a better classification effect. Finally, the simulation of flashover discharge phenomenon characteristics and simulation experiments on a large number of insulator string images demonstrate that the proposed method has high practicality.

Traditional grid analytics heavily rely on accurate power system models, especially dynamic ones for generators, controllers, and loads. However, obtaining comprehensive models is impractical in real operations due to inaccessible parameters and consumer privacy. This necessitates dynamic equivalencing for unknown subsystems, which employs physics-informed machine learning and neural ordinary differential equations (ODE-NET) to preserve dynamic behaviors post-disturbances. The contributions include: 1) A neural dynamic equivalence (NeuDyE) formulation enabling continuous-time, data-driven dynamic equivalence, eliminating the need for acquiring inaccessible system details; 2) Introduction of Physics-Informed NeuDyE learning (PI-NeuDyE) to actively control NeuDyE’s closed-loop accuracy; 3) Driving Port NeuDyE (DP-NeuDyE), a practical application of NeuDyE, reducing the number of inputs required for training. Extensive case studies on the 140-bus NPCC system validate the generalizability and accuracy of both PI-NeuDyE and DP-NeuDyE. These analyses cover various scenarios, including limitations in data accessibility. Test results demonstrate the scalability and practicality of NeuDyE, showcasing its potential application in ISO and utility control centers for online transient stability analysis and planning purposes.

Emotion recognition based on electroencephalography (EEG) signals has garnered substantial attention in recent years and finds extensive applications in the domains of medicine and psychology. However, individual differences in EEG signals pose a challenge to accurate emotion recognition and limit the widespread adoption of such techniques. To address this issue, this study proposes a model that combines random forest weights (RFWs) and four-dimensional convolutional recurrent neural network (4DCRNN) to minimize individual differences and captures emotion-relevant information. By integrating, the proposed model aims to improve the accuracy and generalization capability of emotion recognition. To evaluate the performance of the proposed model, experiments were conducted using the DEAP and SEED datasets. The results demonstrate the effectiveness of the RFW-4DCRNN in emotion recognition. Specifically, the proposed model achieves mean accuracy of 94.98% and 94.21% for Subject-dependent recognition using the DEAP and SEED datasets, respectively. For Subject-independent emotion recognition, the model achieved mean accuracy of 81.70% and 91.12% using two datasets, respectively. The result highlights the capability of the RFW-4DCRNN to effectively recognize emotions and improves generalization performance. Overall, this study presents an approach to addressing individual differences in EEG-based emotion recognition. The RFW-4DCRNN demonstrates promising results in terms of accuracy and generalization capability, offering potential for the advancement and application of emotion recognition techniques.

In short-term load forecasting, deep learning models with recurrent units are widely used. For Long Short-term Memory (LSTM) models, in terms of the input features at one particular time-step, there is a weight series for each input feature. Hence, an input feature with a larger value of weight can be regarded as more important to the final forecasting result. Since the weights of the features are time-invariant, the model considers the input features as equally important at each time step, thus lack of the capability of reflecting the importance fluctuation through the time span. To tackle this issue, this paper proposes a forecasting scheme, which integrates mutual information (MI) into bi-directional long short-term memory (BILSTM) network. The MI method is used to extract the importance value of input features at different time-steps, and constitute the fluctuation matrix of the importance values for input features, which is used as coefficients to correct the original input feature. The corrected features are substituted into the BILSTM network, which further improves the forecasting accuracy. Numerical experiments have been carried out based on real-world load data. The results demonstrate the superior performance of the proposed scheme compared with a series of state-of-the-art methods and thus indicate the importance and effectiveness of capturing the fluctuation of the importance value.

UAV aerial images of insulators have problems such as complex backgrounds, small targets, and obscured targets, resulting in low detection accuracy of insulator targets. In order to solve the above problems, a HRD-YOLOX (Hybrid Attention Mechanisms, Regularization, and Depth Separable Convolution for YOLOX) algorithm suitable for recognizing insulators and detecting defects is proposed based on the YOLOX network. First, the hybrid attention module HAM-CSP (Communication Sequential Processes for Hybrid Attention Mechanisms) is incorporated into the feature extraction network to suppress the interference from the complex background of insulator pictures. Second, the PANet (Path Aggregation Network) structure is replaced with the R-BiFPN(Regularization-Bidirectional Feature Pyramid Network) structure for feature fusion, and an improved regularization module is introduced into the convolutional layer of the BiFPN structure to reduce the overfitting problem of the model and the inference speed of the network. Then, in order to solve the computationally intensive and overfitting phenomenon generated by the detection of small targets such as insulator discharge traces, the DHConv (Deep Separable and Hybrid Attention Mechanisms Convolution) convolution is proposed to be applied to the Conv $3\times 3$ convolutional layer in order to reduce the number of parameters and improve the generalization ability of the model. Finally, the binary cross-entropy function for confidence loss is changed to the Focal Loss function to solve the problem of missed detection and positive and negative sample imbalance due to the image overlap problem The experimental results show that the HRD-YOLOX algorithm improves the average accuracy of insulator detection from 86.23% to 91.34%, and at the same time improves the detection speed from 70.6FPS/S to 82.23FPS/S, which allows real-time detection of insulators, and improves the performance of complex background targets as well as small targets detection.

Insulators play a pivotal role in power transmission lines, and the timely detection of defects in insulators is crucial to prevent potentially catastrophic consequences in terms of human lives and property. This paper proposes an insulator defect detection algorithm, named Insulator Lack-You Only Look Once (IL-YOLO), addressing the limitations observed in existing research concerning the complex background and multi-target challenges in insulator detection. The IL-YOLO algorithm focuses on detecting insulator defects within the intricate background of power transmission lines. To enhance its functionality, we propose three improved modules. Firstly, the Insulator Lack-Global Attention Mechanism (IL-GAM) addresses issues such as the mutual influence of weights and loss of detailed information in the original module. Secondly, the Insulator Lack-C3 (IL-C3) module is designed to emphasize key information while preserving feature extraction and fusion. Lastly, the Insulator Lack-SPPFCSPC (IL-SPPFCSPC) module enhances attention to both key and global information while extracting effective information from multi-scale features. Experimental results demonstrate that IL-YOLO achieves a detection accuracy of 91.2%, marking a 3.6% improvement compared to the YOLOv5 algorithm. Furthermore, precision improves by 0.5%, recall increases by 6.3%, and the F1 score sees a boost of 3.8%. Notably, IL-YOLO achieves a frame rate of 90 frames per second (FPS), showcasing its capacity for real-time detection. Additional experiments affirm IL-YOLO’s accuracy in completing insulator defect detection tasks in both general and complex backgrounds, highlighting its substantial advantages in addressing complex background and multi-target challenges.

A beam-steerable wideband reflectarray antenna (WRA) for $C$ -band high-power microwave (HPM) application is presented in this paper. The $C$ -band WRA comprises a multimode conical horn antenna with high power handling capacity (PHC), $25\times25$ special designed antenna elements, a metal frame and a dielectric plate used as a radome. In our previous work, it has been verified that a wideband prototype using this antenna element has a relative bandwidth of 50% (3.3-5.5 GHz) and its beam scanning range reaches ±60° in low power experiments. In this paper, combined with the equivalent circuit model, the wideband and high PHC property of the WRA element is further explained. To demonstrate the excellent performance of the proposed element in HPM applications, we combined the $C$ -band WRA (which was redesigned from the previous wideband prototype) with a well-designed narrowband HPM source operating at 4.3 GHz, and constructed a matching HPM experimental platform. The $C$ -band WRA works at 4.1-4.5 GHz, and the results of low power experiments indicate that it can maintain good performance during beam scanning. Its sidelobe level and cross-polarization level are always less than −15 dB and −22 dB, respectively, while its maximum aperture efficiency reached 68.99% (the corresponding antenna gain is 28.07 dB at 4.3 GHz). On the other hand, the PHC of the WRA element reaches 3.82 GW/ $\text{m}^{2}$ and the $C$ -band WRA reaches 1.24 GW in simulation. HPM verification experiments have been carried out, and the experimental results show that the PHC of the fabricated prototype exceeded the expectation, which proves that the WRA has broad application prospects in HPM fields.

Cross-domain few-shot classification (CD-FSC) aims to develop few-shot classification models trained on seen domains but tested on unseen domains. However, the cross-domain setup poses a challenge in the form of domain shift between the training and testing domains. Previous research has demonstrated that the encoder can disentangle features into domain-shared and domain-specific features. However, poorly estimated domain-specific features can lead to inadequate generalization on the unseen domain. This paper proposes a disentanglement-and-calibration module (DAC) to address this issue. The disentanglement component separates the features into domain-shared and domain-specific features, while the calibration component corrects the domain-specific features. We demonstrate that the DAC module can significantly enhance the generalization capability of several baseline methods. Furthermore, we show that MatchingNet with the DAC module outperforms existing state-of-the-art methods by 10%-11% when trained on mini-ImageNet, CUB-200, Cars196, Places365 and tested on Plantae dataset.

With the widespread use of distributed systems and the development of big data technology, the storage redundancy, data availability and persistence of distributed systems have become a concern. Traditional multi-copy storage may cause large storage redundancy, thus wasting storage space. The erasure code is considered as the best alternative to the replica strategy. However, the existing methods do not fully consider the access characteristics of files, so that the data with high access popularity are stored using computationally complex erasure codes, resulting in poor parallel read and write performance. Moreover, due to insufficient consideration of file size, storage redundancy cannot be minimized, thus wasting storage space. Therefore, we propose an adaptive hybrid storage strategy based on file access characteristics called FACHS. For cold files, namely the files with low access frequency, we use RS Code (Reed Solomon Code) to store them. RS Code has low computing and storage costs. We use multi-copy and LRC code (local reconstruction code) to store small and large size hot files respectively. Multi-copy ensures the efficiency of file read/write, as well as the ability of parallel read/write. The recovery cost of LRC code in case of node failure is very low. The experimental results show that compared with the existing methods, FACHS can reduce the storage space occupation by 12% for cold files, and improve the read/write speed by 8% and the recovery efficiency by 29% for hot files.

As an important source of inspiration, the great number of patent documents provides designers with valuable knowledge of design rationale (DR), including issues, intent, pros and cons of the solutions. Researchers have carried out a number of data analysis studies based on patent information, which is now a new discipline called Patinformatics, including the analysis of patent information from a macro perspective and the identification and extraction of patent knowledge from a micro perspective. If DR knowledge could be extracted automatically from the patent documents and provided to designers as a source of inspiration, it would greatly promote innovative design, and at the same time promote the reuse of patent documents and the wide application of DR theory, which can be like killing three birds with one stone. To address this issue, this study proposes an improved lexical-syntactic pattern method for DR centric patent knowledge extraction, including DR Vector Space model (DRVS), DRV Trigger Word (DRV-TW), Design Rationale Vector (DRV), DR credibility (DRC) and others, and DRV based knowledge extraction algorithms. Knowledge extraction experiments were conducted on 1491 patent documents to verify the feasibility and performance of the method. In addition, two other sets of comparative experiments were conducted using the FastText and BERT machine learning methods, and the results further confirmed the reliability of the proposed method for low-resource corpus.

Visual guidance is widely used in industrial robots. At present, the traditional method of template matching and positioning is often used in industrial robots under monocular vision guidance. However, for complex workpieces with height differences, if the angle and position of the workpiece are not consistent with the template, the projection will be different, and the positioning accuracy will be obviously reduced. A new method is proposed to solve this problem by dividing the whole contour of the workpiece and using the weighted method of the contour module to correct and match the workpiece image. First, the contour region of the template image is divided according to the position of the grasping points. Then the weight is assigned according to the distance from each contour region to the grasping points. Then, a fast feature point matching method is used to match the initial image of the workpiece to be measured. Finally, accurate contour matching is carried out for each weighted contour region so that the robot can grasp the object accurately. A large number of experiments show that the method has the design requirements of high stability and high accuracy.

An adaptive on-line approximator-based finite-time trajectory tracking scheme is proposed to solve the problem of trajectory tracking of underactuated surface vessel affected by dynamic uncertainties and external disturbances. In this scheme, underactuated transformation is performed by using kinematic virtual control law transformation and bounded constraint. By designing adaptive on-line approximator to approach the upper bound of uncertainty and unknown disturbance, the problem of parameter uncertainty and external disturbance are solved. It is proven by Lyapunov theory that the error signals in the system can converge quickly to the stable region in finite time. Finally, by comparing the simulation results, it is verified that the proposed control scheme can make the underactuated ship track the desired trajectory in finite time. Compared to the traditional control method, the convergence rate of the system error is faster, and it exhibits strong robustness in the face of unknown external disturbances. This has a certain reference value for practical engineering applications.

The construction of hydropower stations has been expanding in China as a result of economic development and the improvement of people's lives. To save cost, the capacity of a single unit has been greatly increased, and many higher technical requirements have been presented for hydropower units, among which one of the key technologies is the thrust bearing. With the increase in single machine capacity, the pv value of the kinetic energy on the thrust bearing also increases, which will cause the bearing tile burning accident. Therefore, the thrust bearing needs to be designed to improve the bearing capacity. Instead of improving the traditional mechanical structure and using new materials, this paper proposes a levitation load reduction device for the thrust bearing to reduce the pv value of the kinetic energy on the thrust bearing. On the basis of kinetic energy analysis, the feasibility of the magnetic levitation load reduction device is analyzed. A repulsive maglev load reduction device suitable for hydropower units is designed; according to linear motor theory, a three-dimensional analytical model is established to analyze the levitation force, and an analytical calculation method is given. A finite element simulation model is built to study the effects of the primary electrical parameters, structural parameters, and material properties on electromagnetic forces, and the effect rules and the methods of optimal design are given. A small-scale prototype was developed, then tests were conducted to verify the feasibility and accuracy of the design and mechanism.

Axis-flux wind generators are widely used in vertical axis wind turbines given their high generator diameter-to-length and power-to-weight ratios, flexible field and winding design, improved cooling, and possibility of modular construction. In this paper, an asymmetric-primary axis-flux hybrid-excitation generator (APAFHG) is proposed to provide a controllable maglev force that compensates for the ripple of axial force fluctuation. First, the operation principle of the proposed generator is introduced. No-load performance influenced by direct current (DC) excitation is obtained by using the 3D finite element method (3D-FEM). Second, the load performances are analyzed under two typical operation statuses, namely, symmetrical pure resistance load and $i_{d}=0$ control strategy load. An alternating current (AC) excitation method is then comparatively analyzed to increase the output power under the maximum armature current. Third, based on the dq axes dynamic mathematical model, the quantitative calculations of levitation force and torque characteristics are deprived and then tested and verified by using the finite element analysis results. These results show that the proposed generator can be implemented for the decoupling control operation of power and levitation forces and is suitable for vertical axis wind turbines.

The safe realization of on-orbit capture remains a challenging task because of uncontrolled service objects, big impact forces, post-impact control, and so on. In this study, based on the relationships between the kinematics and forces established by impedance control, a force constraint function is developed to reduce the contact force during the collision process of capture. Additionally, to realize flexible contact and improve motion performance during the capture process, a control method combining impedance and a sliding mode is designed to make the end-effector exhibit mass-spring-damping behavior after contact with the target, decreasing movement overshoot and stabilization time. Finally, numerical simulations are carried out in a scenario where a planar two-link space robot is utilized to capture a non-cooperative target, and the effectiveness of the proposed method is demonstrated.

This paper proposes a new method to strengthen the nonlinear kinetic complexity and ergodicity of Lorenz system. Through the analysis of auto-correlation, frequency distribution, approximate entropy and information entropy, the improved Lorenz system has better dynamical properties than Lorenz system. According to NIST-800-22 test results, the chaotic sequences generated from proposed system have passed all random tests, which denotes that the improved Lorenz system is applicable to chaotic encryption. Once the plaintext image is color, the size of scramble image is three times as big as plaintext image, so that a lot more pixel information participant in permutation and diffusion to get better encryption results. Simulation results show that the image encryption scheme provides good security and high capacity to resist common attacks.

Current mainstream pedestrian detectors tend to profit directly from convolutional neural networks (CNNs) that are designed for image classification. While requiring a large downsampling factor to produce high-level semantic features, CNNs cannot adaptively focus on the useful channels and regions of the feature maps, which limits the accuracy of pedestrian detection. To obtain a higher accuracy, we propose a single-stage pedestrian detector with channel and spatial attentions (CSANet), which can locate useful channels and regions automatically while extracting features. The backbone of CSANet is different from that of mainstream pedestrian detectors, which can effectively highlight the pedestrian-likely regions and suppress the background. Specifically, we model contextual dependencies from channel and spatial dimensions of the feature maps, respectively. The channel attention module can selectively promote CNNs to focus on key channels by integrating associated features. Meantime, the spatial attention module can illuminate semantic pixels by aggregating similar features of all channels. Eventually, the two modules are connected in series to further enhance the representation of feature maps. Experiment results show that CSANet achieves the state-of-the-art performance with $MR^{-2}$ of 3.55% on Caltech dataset and obtains competitive performance on CityPersons dataset while maintaining a high computational efficiency.

Numerous researches have been done to develop ASV (Autonomous Surface Vessel) collision avoidance systems. Most of the systems used static methods but did not apply a knowledge base where solutions can be reused and adapted to solve a new case. In this paper, an algorithm of autonomous collision avoidance is proposed considering steering dynamic for ASV. The process of this learning method is to recall the FCBR (Fuzzy Case Base Reasoning) containing basic expert knowledge in the form of stored cases. The solutions will be retrieved from the knowledge base to find a NH (New Heading) command for collision avoidance. Moreover, to execute the NH, a design of adaptive fuzzy ASV heading control system based on command filter is conducted considering the input saturation constraints and external disturbances. T-S fuzzy logic is employed to approximate nonlinear uncertainties existing in the heading control system adopting the MLP (Minimal Learning Parameter) technique. Finally, simulations prove that the method is effective to retrieve the past similar cases for the new collision avoidance situation and give its solution for ASV to track adjusted heading.

This paper proposes a hybrid lane occupancy rate prediction model called 2LayersCapsNet, which combines the improved capsule network and convolutional neural networks (CNNs). The model uses CNNs to mine the spatial-temporal correlation characteristics of the lane occupancy rate and then uses an improved capsule network to mine the interrelationships in traffic data measured by sensors in continuous time intervals to predict the lane occupancy rate. The model can solve the problem of CNNs losing important spatiotemporal information caused by the maximum pooling operation and can obtain better prediction results. To verify the efficiency of the 2LayersCapsNet model, the model is compared with the capsule network model (CapsNet), convolutional neural networks model (CNNs), recurrent neural networks model (RNNs), long short-term memory model (LSTM) and stacked autoencoders model (SAEs) with similar network structures and parameter settings on the PEMS-SF data set. The experimental results indicate that the 2LayersCapsNet model can obtain a prediction model faster than the CapsNet model and that 2LayersCapsNet performs better than the CNNs, RNNs, LSTM and SAEs with respect to three evaluation metrics, namely, MAPE, MAE and RMSE, on four prediction tasks.

WLAN-based localization is widely adopted for mobile positioning, which is the prerequisite for location based services and more. However, the existing positioning systems are vulnerable to location spoofing attacks, which may bring major privacy concerns to mobile social network service (MSNS). In this paper, we first show a privacy attack model base on spoofing attack in MSNS, and then propose a novel defense mechanism based on WiFi-hotspot tags (i.e. base-station tags, BS tags). Specially, we utilize the unpredictability and reproducibility of BS tags to authenticate the spatial-temporal property of a geolocation. Furthermore, we introduce the bloom filter to compress parts of real-time hotspots frames, while guaranteeing its high entropy. Also, we design a tag verification algorithm based on the fuzzy extractors, which can well adapt to the high-bit error rates of wireless transmission. Finally, the safety and feasibility of the mechanism are proved by theoretical and experimental analysis.

As one of the key components in mechanical systems, rotatory machine plays a significant role in safe and stable operation. Accurate prediction of the Remaining Useful Life (RUL) of rotatory machine contributes to realization of intelligent operation and maintenance for mechanical manufacturing. In order to overcome the limitations of traditional machine learning algorithms in dealing with complex nonlinear signals, a novel prediction framework for RUL of rotatory machine based on deep learning is proposed in this paper. One-dimensional convolutional neural network is utilized to extract local features from the original signal sequence. In addition, the proposed framework analyzes sensor signals and predicts RUL by combining Long Short-Term Memory (LSTM) network with attention mechanism. Multi-layer LSTM is set up to extract useful temporal features layer by layer and improve the robustness of the model, while attention mechanism is able to effectively solve the problem of information loss in the long-distance signal transmission of LSTM. Through the feature extraction of multi-layer LSTM and the strong supervision ability of attention mechanism, the RUL of rotatory machine can be accurately predicted. The experimental results show that the proposed method for RUL estimation is efficient and has higher prediction accuracy than the traditional machine learning algorithms.

The rapid development of communication technologies, the network, advanced computing methods and wireless medical sensors gives rise to a modern medical system. In this system, large-scale electronic health records (EHRs) are often outsourced to be stored at the third parties, such as cloud service providers (CSPs). However, CSPs are not trustworthy, that is, serious security and privacy concerns about cloud service exist because it may expose the user's sensitive data to CSPs or unauthorized users in transmission, storage and sharing. To prevent the privacy disclosure of patients better and realize information sharing more effectively, this paper proposes an anonymous EHRs sharing scheme based on decentralized hierarchical attribute-based encryption (ABE). In the proposed scheme, (1) Multiple attribute authority (AA) ABE is leveraged to achieve fine-grained and scalable data access control and avoid bottleneck. Meanwhile, hierarchical access tree is used to encrypt multiple files in one operation, thereby saving calculation and storage load greatly. Moreover, the hidden access policy enhances user privacy protection. (2) The global identifier (GID) of a user is introduced to resist the collusion attack of users. Subsequently, an anonymous key generation mechanism is equipped to prevent multiple AAs from building a full profile using the user's GID. (3) To ensure the correctness and integrity of EHRs, users can conduct double verification based on the verification tag and convergent key. Finally, the efficiency analysis and experiments show that the scheme meets the security requirements of key management and privacy preservation in cloud and is proven secure and efficient in practice under the decisional bilinear Diffie-Hellman (DBDH) assumption.

In accordance with the dynamically changing characteristics of user application load demand, the optimization of energy consumption in the process of virtual machine automatic deployment on the basis of the effective integration of user personalized resource demand in cloud platforms and the dynamic migration technology of virtual machines is studied in this work. Aiming at the problem of energy consumption optimization, an energy-efficient virtual machine deployment framework, which can be dynamically adjusted in accordance with the user's actual resource needs, is designed. In the virtual machine deployment framework, this paper presents a virtual machine deployment selection algorithm based on a double-cursor control mechanism for the resource usage state of CPU and memory, which achieves a binocular optimization balance to a certain extent. Simulation experiment results show that when the virtual machine deployment framework proposed in this paper and the virtual machine deployment selection algorithm based on a double-cursor control mechanism are combined, the number of necessary active physical nodes in the cloud data center can be effectively controlled, and the frequency of virtual machine migration synchronization can be reduced. Consequently, the cloud data center can maintain low energy costs.

This paper proposes an intelligent recognition method for shearer cutting state based on deep learning theory, to solve the problems where the picks are prone to various failure forms during the cutting of coal and rock masses by the shearer. The failure will lead to the decline on the stability of the entire machine of the shearer and affect the safety production. Specially, a 1:1 simulation bench is used for simulating underground mining conditions to measure and collect the cutting loads of picks and establish a sample database. Deep learning-based intelligent recognition method is an effective tool that can break away from the dependency of prior knowledge and recognition experience, and sparse. In this paper, a promising deep learning method called sparse filtering is proposed for intelligent recognition of shearer cutting. So sparse filtering is applied to construct an automatic feature extraction model, and softmax regression is adopted as a classifier for cutting pick state recognition. Furthermore, L1/2 regularization term is added to the cost function of sparse filtering to prevent the problem of excessive model training and weights. The proposed method for identifying the cutting status of the shearer can effectively monitor the cutting status of the picker, thereby improving the safety and stability of the cutting of the shearer and promote the coal mining efficiency.

An auto-berthing control strategy for 3-DOF (degrees of freedom) underactuated marine surface vehicles based on concise backstepping is presented in this paper. Firstly, differential homeomorphic method is used to simplify and make the 3-DOF underactuated marine surface vehicle motion model without external disturbances and model uncertainties has the structure of the general nonlinear system. Then, an auto-berthing controller for the transformed marine surface vehicle model is designed based on the backstepping, dynamic surface control (DSC) technology and Lyapunov direct method. The concise backstepping method can not only simplify the design process of the nonlinear controller but decrease the number of design parameters. Further, in order to illustrate the robustness of the designed controller, simulation experiments are carried out under the external disturbances. Theoretical analysis is provided to prove that the designed controller has a concise structure and is easy to implement in engineering. In addition, it can ensure that all signals of the system are bounded. Simulation results illustrate the effectiveness of the developed control scheme.

Fuzzy information is generally represented by fuzzy set (FS). Pythagorean fuzzy set (PFS), as a new extension of FS, can represent fuzzy information more effectively. The accuracy of fuzzy information represented by PFS directly affects the result of information processing. Generalized parameter (GP), expressed by Pythagorean fuzzy number, can judge the accuracy of fuzzy information represented by PFS. However, for complex fuzzy application problems, a single GP cannot comprehensively judge the fuzzy information, and the GP may also be wrong. Therefore, the concept of group generalized parameters (GGPs) is proposed. The GGPs can comprehensively judge the accuracy of fuzzy information, and can avoid the influence caused by the error of a certain GP. In order to effectively aggregate the fuzzy information and the GGPs, some new group generalized Pythagorean fuzzy aggregation operators are proposed, including group generalized Pythagorean fuzzy weighted average (GGPFWA) operator and group generalized Pythagorean fuzzy weighted geometric (GGPFWG) operator. The definitions, theorems and properties of GGPFWA operator and GGPFWG operator are given and proved. In this paper, GGPFWA operator and GGPFWG operator are applied to solve decision making problems, and their effectiveness and feasibility have been verified by three cases of pattern recognition, medical diagnosis and multiple criteria decision making.

The increasing abundance of data in the trajectories of personal movement opens up new opportunities for analyzing and mining human mobility. But the inherent personal information in the data raises the privacy concern. In this paper, the trajectories are not simply considered as a sequence of the coordinates in Euclidean space, they combine the semantics-aware information with the background knowledge of underlying map for the location points. A novel approach is then proposed to conceal the actually visited sensitive places. To this end, a cloaking region for each personalized sensitive place is built before a reasonable dummy trajectory in the cloaking region is constructed. The performance of our approach is evaluated based on a real-world trajectories dataset. And the results show that the proposed approach outperforms the existing privacy-preserving approaches.

Granular computing has the advantage of discovering complex data knowledge, and manifold alignment has proven of great value in a lot of areas of machine learning. We propose a novel algorithm of fuzzy granule manifold alignment (FGMA), where we define some new operations, measurements, and local topology of fuzzy granular vectors in fuzzy granular space. Furthermore, the algorithm is very different from Semi-supervised and Procrustes algorithm because predetermining correspondence is not necessary. A projection is learned that can map instances described by two types of features to a low-dimensional space. Meanwhile, the local topology of the fuzzy granular vector induced by the instance is also preserved and matched within each set in lower dimensional space. This approach makes it possible to directly compare between data instances in different spaces. We convert an alignment problem of data in feature space into fuzzy granular manifold alignment problem of granular space. Specifically, we first define fuzzy granule, fuzzy granular vector, operations, and measurements in fuzzy granular space and gave proofs of theorems and deductions. Next, the local topology around the fuzzy granular vector is introduced and the optimal local topology matching can be achieved by minimizing their Frobenius norm. Finally, two manifolds are connected and the optimal mapping can be calculated to obtain dimensionality reduction of the joint structure. Thus, the corresponding relationship between two data instances can be got. We verified this algorithm in Oxford image and Alzheimer's disease voice dataset. Theoretical analysis and experiments demonstrate the algorithm proposed is robust and effective.

Whale optimization algorithm (WOA) is a population-based meta-heuristic imitating the hunting behavior of humpback whales, which has been successfully applied to solve many real-world problems. Although WOA has a good convergence rate, it cannot achieve good results in finding the global optimal solution of high-dimensional complex optimization problems. The learning mechanism of Lamarckian evolutionism has the advantages of speeding up and strengthening local search. Through this learning mechanism, solutions with certain conditions can acquire higher adaptability with a higher probability by active learning. To enhance the global convergence speed and get better performance, this paper presents a WOA based on Lamarckian learning (WOALam) for solving high-dimensional function optimization problems. First, the population is initialized by good point set theory so that individuals can be evenly distributed in the solution space. Second, the upper confidence bound algorithm is used to calculate the development potential of the individual. Finally, based on the evolutionary theory of Lamarck, individuals with more development potentials are selected to perform the local enhanced search to improve the performance of the algorithm. The WOALam was compared with six variants of WOA on 44 benchmark functions. The experiments proved that the proposed algorithm can balance the global exploring ability and the exploiting ability well. It could obtain better results with fewer iterations and had good convergence speed and accuracy.

The key to leak detection and location in water supply pipelines is signal denoising and feature extraction. First, in this paper, an improved spline-local mean decomposition (ISLMD) is proposed to eliminate noise interference. Based on the ISLMD decomposition of a signal, the cross-correlation function between the reference signal and the product functions component can be obtained. And then the PF component containing the leak information can be extracted reasonably. Compared with improved local mean decomposition, the ISLMD has higher accuracy in leak location. Second, an image recognition method using a convolutional neural network for leak detection is proposed, which can better address the problem that the features of different leak apertures or locations are highly similar to each other. The images from the conversion of the reconstructed signals are used as the input of the AlexNet model, which is capable of adaptive extraction of leak signal features. The trained AlexNet model can effectively detect different leak apertures. Finally, the signal time-delay between the upstream and downstream pressure transmitters caused by the leak and propagation of negative pressure wave is determined according to generalized cross-correlation analysis, and thereby, the leak location is obtained. The experimental results show that the proposed method is effective for leak detection and location.

The backstepping control is a kind of nonlinear controller design algorithm. To simplify the nonlinear controller design process, decrease the number of undetermined parameters, improve the robustness, and reduce the energy consumption of the course-keeping controller for ships, an improved concise design method is proposed by introducing an arctan nonlinear function passed through by course error signal under the backstepping design framework, while the design process of the controller is simplified to only one step. The simulation results indicate that, compared with the backstepping-based controller, the maximum response performance (quantified by the mean absolute error) under the proposed controller increases by 57.8%, the maximum energy cost performance (quantified by the mean integral absolute) reduces by 28.6% and the maximum smoothness performance (quantified by the mean total variation) reduces by 44.3% with the strong ability of disturbances rejection. The algorithm given in the note has advantages of the simple design process, strong robustness, and low energy consumption.

In this paper, a nonlinear parallel control algorithm is developed for an electro-hydraulic actuator to achieve high velocity tracking performance and reduce energy consumption. The parallel control system consists of a servo valve and a variable displacement pump. A separate strategy is employed for practical use. The variable displacement pump is considered as feedforward according to velocity commands and leakage; while the servo valve is used to improve the dynamics and accuracy of the closed loop system. Two disturbance observers are employed to deal with the uncertainties and disturbance in the control process. A radial basis function neural network (RBFNN)-based extended disturbance observer is proposed to compensate for the unknown parameters and disturbance in the velocity control loop. To attenuate the influence of model uncertainties and disturbance in the pressure control loop, a nonlinear disturbance observer is adopted. The stability of the whole system is proved through the Lyapunov theory. The comparative experiments are conducted to verify the effectiveness of the proposed nonlinear parallel controller. The results demonstrate that the proposed algorithm can improve the velocity tracking performance for a valve-pump parallel controlled electro-hydraulic actuator under uncertainties and disturbance.

Human motion synthesis technology has a very important position in computer animation, and it is widely used in medicine, film and television, motion analysis, games, and other related fields. The synthesis of human motion is the virtual of the action of the characters in the real world, the authenticity of the action, and the natural smoothness is especially important to the user's experience. Due to the complexity of human structure, how to generate a high-quality movement is a challenging task. The data used in this paper are all 3D human motion data in BioVision Hierarchical (BVH) format, which can be captured by optical, inertial, mechanical or other video-based motion capture devices. In this paper, first, a three-layer convolutional neural network was used to output mapping in the hidden unit of the input motion capture data. Then, a one-dimensional convolution auto-encoder was connected; meanwhile, the bone length constraint, position constraint, and trajectory constraint were added. It repaired the non-inertial joints of motion data and removed the motion artifacts. To achieve the synthesis of the two motions, we extracted the style transformation in the motion, added style and content constraints, and finally output the motion. To verify the feasibility of the algorithm, we obtained the animation effect of the synthesized motion by testing the input motion. The experimental results show that the motions synthesized by the proposed algorithm not only look natural smooth in visual effect but also reduce the time consumed by about 42.6% compared with the existing algorithms.

DNA computing proposed by Adelman is new biotechnology which provides a new way to solve NP-hard problem. It has a promising future and successful results of various applications. DNA codes design is a significant step in DNA computing. Therefore, reliable DNA codes design not only can avoid non-specific hybridization between a code and its Watson-Crick complement but also can improve the efficiency of DNA computing. In this paper, a new algorithm is proposed to design reliable DNA codes. This algorithm combines the Bat algorithm and PSO algorithm. Fast nondominated sorting is used to assign a rank for codes. Thus, it is called BPSON for short. A bat algorithm is used to overcome PSO fall into the local optimal solution and enhance global search ability. In addition, for the purpose of verifying the effectiveness of our algorithm, the performance of BPSON is compared with the previous works. The experimental results show that codes obtained by our algorithm can avoid the appearance of secondary structure, which is beneficial to the specific hybridization among codes and has better thermodynamic properties. The results show that our algorithm can provide optimal codes for DNA computing.

Embedding second-order operations into deep convolutional neural networks (CNNs) has recently shown impressive performance for a number of vision tasks. Specifically, the two-branch second-order response transform (SoRT) network introduces the element-wise product transform into intermediate layers of CNNs, which facilitates the cross-branch response propagation and achieves promising classification accuracy. However, it fails to adaptively rescale responses of feature maps and largely changes the topology of the original backbone networks, leading to the limitation of generalizability. In order to overcome above problems, we propose a novel Second-order Response Transform Attention Network (SoRTA-Net) for classification tasks. The core of SoRTA-Net is the designed refined second-order response transform (RSoRT) module integrating reasonably the attention Squeeze-and-Excitation (SE) block and second-order response transform. Firstly, SoRTA-Net recalibrates adaptively feature responses by the SE block, and then the outputs are sequentially passed through the second-order response transform block, capturing approximately co-occurrence statistics and providing more nonlinearity. Finally, a shortcut branch is naturally combined with the output of the module to boost propagation. The proposed RSoRT module can be flexibly inserted into existing CNNs without any modification of network topology. Our SoRTA-Net extensively evaluated on three datasets (CIFAR-10, CIFAR-100, and SVHN). The experiments have shown that SoRTA-Net is superior to its baseline and achieves competitive performance.

In the field of social network, fast detection of the burst topic plays a decisive role in emergency response and disposal. However, social data are noisy and sparse, which evolves with time going on and space changing make it difficult to catch the instant semantics with traditional methods. Instead of passively waiting for an emergency topic, we try to detect the latent burst topic in its budding stage. In this paper, we propose a fast burst topic detect method, namely, FBTD, which aligns data prediction with characteristic calculation to detect burst term from the real-time spatial-temporal data stream and integrates local topic detection with global topic detection to find the spatial-temporal burst topic. Our method controls the delay within a 0.1 s level while preserving the topic quality. The experiments show that preferable effects are procured, and our method outperforms the state-of-the-art approaches in terms of effectiveness.

High-utility itemset mining (HUIM) is an important research topic in the data mining field. Typically, traditional HUIM algorithms must handle the exponential problem of huge search space when the database size or number of distinct items is very large. As an alternative and effective approach, evolutionary computation (EC)-based algorithms have been proposed to solve HUIM problems because they can obtain a set of nearly optimal solutions in limited time. However, it is still time-consuming for EC-based algorithms to find complete high-utility itemsets (HUIs) in transactional databases. To address this problem, we propose an HUIM algorithm based on an improved genetic algorithm (HUIM-IGA). In addition, a neighborhood exploration strategy is proposed to improve search efficiency for HUIs. To reduce missing HUIs, a population diversity maintenance strategy is employed in the proposed HUIM-IGA. An individual repair method is also introduced to reduce invalid combinations for discovering HUIs. In addition, an elite strategy is employed to prevent the loss of HUIs. Experimental results obtained on a set of real-world datasets demonstrate that the proposed algorithm can find complete HUIs in terms of the given minimum utility threshold, and the time-consuming of HUIM-IGA is relatively lower when mining the same number of HUIs than state-of-the-art EC-based HUIM algorithms.

This paper aims to estimate the carbon monoxide (CO) and hydrocarbon (HC) concentrations of vehicle exhaust. For this purpose, an improved Stacking model is designed. Compared with individual estimation models, the improved Stacking model can achieve better concentration estimation performance. That model has a three-layer structure. The first layer is made up of multiple estimation models, which produce intermediate estimation results from the original exhaust data based on the $K$ -fold cross-validation. The second layer takes these intermediate estimation results as input and trains a statistical learning model which generates preliminary estimation results of the concerned exhaust concentrations. The first two layers actually constitute the Stacking model, which is extended by the additional third layer of our improved one. The third layer implements a weighted summation method. More specifically, the preliminary estimation results generated by the second layer are linearly combined with the concentration estimation results of some strong estimation models, such as XGBoost and LightGBM, to produce the final estimation results in the third layer. Our improved Stacking model is verified through experimental data, which were collected by a Urban Road Network Vehicle Emissions Monitoring System and small weather stations in two Chinese cities, including Beijing and Jiaozuo. Experimental results show that compared with some regression and neural network estimation models, especially the Stacking model and Boosting models, our improved Stacking model achieves higher exhaust concentration estimation accuracy.

Denoising the Monte Carlo (MC) rendering images is different from denoising the natural images since low-sampled MC renderings have a higher noise level and there are inexpensive by-products (e.g., feature buffers) we can leverage. However, the main challenge is designing a model to fast fuse these feature buffers and reconstruct perceptually noise-free images from noisy MC renderings. In recent years, supervised learning methods remove the noise and reconstruct clean images, but most of them cannot handle MC noise well. In this paper, we introduce an end-to-end CNN model to fuse feature buffers and predict a clean image directly. In addition, we devise a new high-dynamic range (HDR) image normalization method to help us to train the model on HDR images in a more efficient and stable way. We setup a series of experiments for selecting the hyperparameter of our deep learning model, network depth, which can promote our network's performance and avoid overfitting. We demonstrate that our model is robust on a wide range of scenes and can generate satisfactory results in a significantly faster way.

Deep hashing, the combination of advanced convolutional neural networks and efficient hashing, has recently achieved impressive performance for image retrieval. However, state-of-the-art deep hashing methods mainly focus on constructing hash function, loss function and training strategies to preserve semantic similarity. For the fundamental image characteristics, they depend heavily on the first-order convolutional feature statistics, failing to take their global structure into consideration. To address this problem, we present a deep covariance estimation hashing (DCEH) method with robust covariance form to improve hash code quality. The core of DCEH involves covariance pooling as deep hashing representation, performing global pairwise feature interactions. The covariance pooling can capture richer statistic information of deep convolutional features and produce more informative global representations.Due to convolutional features are usually high dimension and small sample size, we estimate robust covariance by shrinking its eigenvalues using power normalization, forming an independent structural layer. Then the structural layer is embedded into deep hashing paradigm in an end-to-end learning manner. Extensive experiments on three benchmarks show that the proposed DCEH outperforms its counterparts and achieves superior performance.

This paper investigates finite-time stabilization of a class of non-affine nonlinear systems with time-varying output constraints, input saturation, and unknown disturbance. Without loss of accuracy, an approximation method is employed to convert the non-affine nonlinear system to an affine-like expression. A novel adaptive terminal sliding mode disturbance observer is proposed to enhance system robustness by estimating unknown compound disturbances in finite time, including external disturbances and system uncertainties. A time-varying barrier Lyapunov function is applied to ensure that constraints are not violated. Backstepping-based controllers are designed to drive tracking errors to zero in finite time. Simulation results demonstrated the effectiveness of the proposed control technique.

At present, searchable encryption is a very promising direction in the field of cloud computing. However, most existing works focus on keyword-based search schemes and regardless of personalized search needs, a keyword-based search does not take into account the user's location information and cannot exactly match users' search intentions. Since location information is very important in mobile searches, we propose a personalized mobile search (PRMS) over encrypted outsourced data, and we convert the user's location information into distance information to generate the user location model, forming a location query matrix with user location information. The matrix is then used to encrypt the user's location query and conceal the location information in the location query matrix. In this paper, we combine a user's interest preference and location information in personalized searches over encrypted outsourced data, adopt the law of universal gravitation to calculate scores of files in the cloud, and return the first K results with the highest gravitational forces. For the first time, we propose a PRMS-improvement scheme that is applied to an encryption method to build the content index and location index, which can greatly reduce the time for model construction. Through the PRMS scheme, we realized personalized mobile searches based on user's interests and location information.

As a class of capacity-approaching codes, nonbinary low-density parity-check (LDPC) codes have attracted much attention because of noticeable performance. Nonbinary LDPC-coded modulation systems which have excellent performance for high-spectral efficiency transmission are also potential schemes in the future communication system. In this paper, we propose a new construction method of quasi-cyclic nonbinary LDPC codes. Furthermore, a comparative study about the performance of various coded systems over the AWGN channel and the high-mobility channel is performed on turbo codes in LTE communications and LDPC codes in 5G standard. Simulation results show that the nonbinary LDPC-coded modulation system is effective for improving the performance of wideband wireless communication systems with orthogonal frequency division multiplexing in the high-mobility scenario.

This paper proposes a time series model based on wavelet transform and long short-term memory (LSTM) network to forecast vehicle emission. It implements the semi-supervised collaborative training regression to compensate missing emissions data. The accumulated carbon monoxide (CO), hydrocarbons (HC), and nitric oxide (NO) concentrations emitted by vehicles in different lanes per hour were taken to quantitatively characterize the vehicle emissions. The original time series of vehicle emission data, which may be highly variable, is decomposed into several lowly variable sub-series by wavelet transform. For each sub-series, an LSTM time series model is proposed to forecast vehicle emissions. More specifically, the inputs of that LSTM model are the weather variables, the driving variables of the concerned vehicle and historical emissions records while its output is the predicted accumulated concentrations of CO, HC, and NO. The three types of predicted concentrations of all sub-series are summed up, respectively, and produce the desired prediction of the total emission of each type. The proposed model is verified through real data which was collected between May 2017 and December 2017 at the multi-lane monitoring station of Baimiao South Road, Daxing District, Beijing, China. It confirms that our model based on wavelet transform and LSTM can efficiently improve the correlation coefficient (R) and the index of agreement (IA) against conventional models, such as ARIMA and wavelet-ARIMA model.

Reversible bimolecular chemical reactions are elementary chemical reactions. This paper investigated this reaction type based on DNA strand displacement, and proposed degradation, catalysis, and annihilation reactions along with the synchronization reaction modules. DNA reaction modules were compared with ideal reaction modules, and relative reaction rates analyzed using the Lotka-Volterra oscillator as an example to demonstrate the validity of these reaction modules. An arbitrary chemical reaction network was employed to numerically simulate and predict synchronization between two Lotka-Volterra oscillators.

Bijective connection (BC) networks, including a family of interconnection networks of multiprocessor systems, have been studied extensively due to its desirable properties, such as lower diameter, high reliability, and diagnosability. To meet the demand of processing integrating tasks with large-scale and complex architectures, it is significant to explore alternative interconnection networks for multiprocessor configuration. To this end, we propose a novel framework called hyper bijective connection network (HBC network) as an extension of BC networks, which allows to study the properties of other potential interconnection networks in unity rather than in individual. We prove that when n ≥ 3, m ≥ 2, every n-dimensional HBC network Hn(m) has (edge) connectivity m + n - 2, super connectivity 2n + m - 4, and super edge-connectivity 2n + 2m - 6, and is super-connected and super-edge-connected. These results indicate the high reliability of HBC networks. Moreover, we analyze three classic diagnos abilities of a HBC network, including tp-, t1/t1-, and t/k-diagnosability. We show that when n ≥ 3 and m ≥ 2, an n-dimensional HBC network Hn(m) is (m + n - 2)-diagnosable, (2n + m - 4)/(2n + m - 4)-diagnosable, and t(m, n, k)/k-diagnosable, where 0 ≤ k ≤ m + n - 2 and t(m, n, k) = (k + 1)n + (m - 2) - ((k + 1)(k + 2)/2) + 1. Besides, it is shown that the corresponding properties for BC networks can be derived naturally as special cases of that for HBC networks.

The design of DNA codes sets satisfying certain combinatorial constraints is important in reducing hybridization errors due to nonspecific hybridization between distinct codes and their complements in DNA computing, data encryption, and data storage. The DNA code design problem is to find the largest possible set of DNA codes. In this paper, we present a Bloch quantum chaos algorithm for the designing DNA codes sets. The algorithm uses the chaotic equation to initialize the Bloch coordinates of quantum bits, next adopts the whole interference crossover strategy to get crossover operation, then employs quantum non gate strategy to get mutation operation, finally utilizes the dynamic adjustment strategy to adjust the quantum rotation corner. Several experimental results in which our algorithm finds DNA codes sets match or exceed the best previously known constructions.