Search

Finite element method is an important method to solve mathematical problems in engineering. Many mathematical equations are difficult to solve, but it becomes very simple after using the finite element method. In this paper, the finite element method is applied to the calculation of gravity anomaly. First, the variational equation of gravity anomaly calculation is established, and then the gravity anomaly value ten times the distance away from the anomaly body is used as the boundary condition. By comparing the gravity anomaly obtained by solving the stiffness matrix with the analytical solution, it can be found that the method in this paper has high accuracy. Finally, the model of Jinchuan copper nickel deposit is used for calculation, and the calculated gravity anomaly field is inverted with Growth3D. It can be found that the inversion result is very close to the model, which verifies the effectiveness of the algorithm in this paper. [ABSTRACT FROM AUTHOR]

Quantitative analysis of the flow field is an effective method to study hydrodynamics. As a flow field measurement technology, the Background Oriented Schlieren (BOS) is widely used. However, it is difficult to measure the complex transparent flow field (flow field with large refractive index gradient) using the BOS experiment. In order to overcome this difficulty and improve the accuracy of the BOS experiment, this paper presents a hybrid adaptive wavelet-based optical flow algorithm for the BOS. The current algorithm is a combination of the traditional optical flow algorithm and the wavelet-based optical flow algorithm. By adding the initial value constraints, the adaptive scale constraints, and the adaptive regularization constraints, the algorithm can effectively overcome the above-mentioned difficulty and also improve its accuracy. To further illustrate the feasibility of the proposed method, this paper uses the simulation data, the data of the DNS datasets, and the data of the BOS experiment to verify the performance of the algorithm. The experiment of comparing the proposed algorithm with the existing ones is carried out on the DNS datasets and the data of the BOS experiment. Finally, the proposed method is verified by a practical BOS experiment. The results show that the proposed algorithm can effectively improve the measurement accuracy of displacements. [ABSTRACT FROM AUTHOR]

Leach (low energy adaptive clustering hierarchy) algorithm is a self-clustering topology algorithm. Its execution process is cyclical. Each cycle is divided into two phases: cluster building phase and stable data communication phase. In the stage of cluster building, the adjacent nodes cluster dynamically and randomly generate cluster heads. In the data communication phase, the nodes in the cluster send the data to the cluster head, and the cluster head performs data fusion and sends the results to the aggregation node. Because the cluster head needs to complete data fusion, communication with the convergence node and other works, the energy consumption is large. Leach algorithm can ensure that each node acts as cluster head with equal probability, so that the nodes in the network consume energy relatively evenly. The basic idea of Leach algorithm is to randomly select cluster head nodes in a circular way. It evenly distributes the energy load of the whole network to each sensor node in the network. It can reduce network energy consumption and improve network life cycle. Leach repeatedly performs cluster refactoring during its operation. This paper studies the parameter detection of wireless sensor network based on Leach algorithm on the on-chip embedded debugging system. Because the classical low-power adaptive clustering layered protocol (Leach) has the problem of energy imbalance and short node life cycle, this paper uses embedded debugging technology based on Leach algorithm and the residual energy and position of nodes in wireless sensor networks were tested for research. This Leach algorithm uses the concept of wheel. Each round consists of two phases: initialization and stabilization. In the initialization stage, each node generates a random number between 0 and 1. If the random number generated by a node is less than the set threshold T (n), the node publishes a message that it is a cluster head. Through the research on the parameter detection, the simulation results show that the research in this paper has good feasibility and rationality. [ABSTRACT FROM AUTHOR]

During the development of deep neural networks (DNNs), it is difficult to trade off the performance of fitting ability and generalization ability in training set and unknown data (such as test set). The current solution is to reduce the complexity of the objective function, using regularization methods. In this paper, we propose a method called VOVU (Variance Of Variance of Units in the last hidden layer) to maximize the optimization of the balance between fitting power and generalization during monitoring the training process. The main idea is to give full play to the predictability of the variance of the hidden layer units in the complexity of the neural network model and use it as a generalization evaluation index. In particular, we take full advantage of the last layer of hidden layers since it has the greatest impact. The algorithm was tested on Fashion-MNIST and CIFAR-10. The experimental results demonstrate that VOVU and test loss are highly positively correlated. This implies that a smaller VOVU indicates that the network has better generalization. VOVU can serve as an alternative method for early stopping and a good predictor of the generalization performance in DNNs. Specially, when the sample size is limited, VOVU will be a better choice because it does not require dividing training data as validation set. [ABSTRACT FROM AUTHOR]

In order to solve the declining influence of traditional cultural symbols, the research on traditional cultural symbols has become more meaningful. This article aims to study the application of traditional cultural symbols in art design under the background of artificial intelligence. In this paper, a fractal model with self-combined nonlinear function changes is constructed. By combining nonlinear transformations and multiparameter adjustments, various types of fractal models can be automatically rendered. The convolutional neural network algorithm is used to extract the characteristics of the style picture, and it is compared with the trained picture many times to avoid the problem of excessive tendency of the image with improper weight. The improved L-BFGS algorithm is also used to optimize the loss of the traditional L-BFGS, which improves the quality of the generated pictures and reduces the noise of the chessboard. The experimental results in this paper show that the improved L-BFGS algorithm has the least loss and the shortest time in the time used for more than 500 s. Compared with the traditional AdaGrad method, its loss is reduced by about 62%; compared with the traditional AdaDelta method, its loss is reduced by 46%. Its loss is reduced by about 8% compared with the newly optimized Adam method, which is a great improvement. [ABSTRACT FROM AUTHOR]

This paper examined the three-dimensional steady thin film flow of tangent hyperbolic fluid with nonlinear mixed convection flow and entropy generation past a stretching surface under the influence of magnetic field. For the flow problem, the Cattaneo–Christov heat and mass diffusion model was employed to examine heat and mass transfer characteristics and impacts of the normally directed magnetic field. To transform nonlinear PDEs into ODEs, the variable transformation technique was used. The bvp4c algorithm was implemented to solve these ODEs. The behavior of every leading parameter on the velocities, temperature, concentration profile, entropy generation, and Bejan number was reported with tabular and figurative form. The results show that as the values of Br increase, the entropy generation enhances, but the Bejan number decreases. Moreover, as the values of B increase, the opposite characteristics are observed in entropy generation and Bejan number graphs. Furthermore, the skin friction coefficient number, local Nusselt number, and Sherwood number are graphically discussed for the active involved parameters. The best agreement is recorded when we compare this paper with the previous literature for various values of M. [ABSTRACT FROM AUTHOR]

When the strapdown inertial navigation system does not perform coarse alignment, the misalignment angle is generally a large angle, and a nonlinear error model and a nonlinear filtering method are required. For large azimuth misalignment, the initial alignment technology with a large azimuth misalignment angle is researched in this paper. The initial alignment technology with a large azimuth misalignment angle is researched in this paper. First, the SINS/GPS nonlinear error model is established. Secondly, in the view of observation gross errors and inaccurate noise statistical characteristics, an adaptive robust CKF algorithm is proposed. Finally, according to the simulation analysis and experiment, the adaptive robust CKF algorithm can augment the stability and improve the filter estimation precision and convergence rate. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet, data information has begun to spread rapidly on the Internet, and the types and fields involved are becoming more and more diverse. With the deepening of internationalization, English information has also become a common entry for tourism. Relatively speaking, the translation of English documents is also on the agenda. The intricate literature information has put forward a more specialized and vertical demand for retrieval. Traditional retrieval systems usually use string matching algorithms to search, but this technology cannot perform semantic expansion of query conditions. In the case of "multiple words with one meaning" and "polysemy of one word," the retrieval accuracy of traditional retrieval systems decreases. In order to solve the previously mentioned problems, this study proposes semantic retrieval based on domain ontology technology. The purpose of semantic retrieval is to semantically expand the user's query conditions on the basis of accurately understanding the retrieval conditions. At the same time, with the help of the constructed domain ontology, it provides more accurate and comprehensive retrieval services for document retrieval. The experimental results of this study show that, for the clustering of the entire dataset, the number of ontology concepts in each article is 61% of that, before merging, which effectively reduces the complexity of the semantic network model. Therefore, the validity of the ontology concept merging algorithm proposed in this study is verified. [ABSTRACT FROM AUTHOR]

Image text description is a multimodal data processing problem in the computer field, which involves the research tasks of computer vision and natural language processing. At present, the research focus of image text description task is mainly on the method based on deep learning. The work of this paper is mainly focused on the imprecise description of visual words and nonvisual words in the description of image description tasks in the image text description. An adaptive attention double-layer LSTM (long short-term memory) model based on coding-decoding is proposed. Compared with the algorithm based on the adaptive attention mechanism based on the coding-decoding framework, the evaluation index BLEU-1 is improved by 1.21%. The METEOR was 0.75% higher and CIDEr was 0.55%, while the indexes of BLEU-4 and ROUGE-L were not as good as those of the original model, but the index was not different. Although it cannot surpass all the performance indicators of the original model, the description of visual words and nonvisual words is more accurate in the actual image text description. [ABSTRACT FROM AUTHOR]

In recent years, there have been constant disputes over college student cadres. Starting from the public opinion crisis of College Students' autonomy and using the "K-core" algorithm, this paper found that the college student cadres could not realize their own correct roles. The fuzzy cognitive map (FCM) model was used to analyze 49 influencing factors of N University's retreat action. It is found that the five factors of mass support, ability, ideology and morality, work tasks, and performance evaluation are important factors leading to the retreat action. This research proposes role reconstruction and system rectification strategies for the five variables in order to achieve a true feeling of student autonomy and good governance. [ABSTRACT FROM AUTHOR]

Many optimization algorithms have been applied to solve high-dimensional instances of the 0-1 knapsack problem. However, these algorithms often fall into a local optimization trap and thus fail to obtain the global optimal solutions. To circumvent this shortcoming, a hybrid harmony search algorithm with distribution estimation is proposed in this paper. A few important features of the proposed algorithm are as follows: (i) the idea of probability distribution estimation is employed to design the adaptive search strategy, (ii) a fixed improvisation process is presented to improve the algorithm searching ability, (iii) a new method of initialization is used to ensure that the initialization is feasible harmony and (iv) an improved remediation approach is proposed to effectively repair the infeasible solutions. To assess the effectiveness of the proposed algorithm, some experiments are carried out. The experimental results reveal that the proposed algorithm is a reliable and promising alternative for solving the 0-1 knapsack problem. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy and performance of traditional image threshold segmentation algorithm, this paper proposes a multithreshold segmentation method named improved Harris hawk optimization (IMHHO). Firstly, IMHHO adopts Tent map and elite opposition-based learning to initialize population and enhance the diversity. Secondly, IMHHO uses quadratic interpolation to generate new individuals and enhance the local search ability. Finally, IMHHO adopts improved Gaussian disturbance method to disturb optimal solution, which coordinates the local and global search ability. Then, the performance of IMHHO is tested based on 14 benchmark functions. In image segmentation, different algorithms are tested to compare the comprehensive performance based on Otsu and Renyi entropy. Experiments show that IMHHO performs better in the three kinds of benchmark functions; the segmentation effect is directly proportional to the number of thresholds; compared with other algorithms, IMHHO has better comprehensive performance. [ABSTRACT FROM AUTHOR]

To address automatic detection of pedestrian fall events and provide feedback in emergency situations, this paper proposes an attention-guided real-time and robust method for pedestrian detection in complex scenes. First, the YOLOv3 network is used to effectively detect pedestrians in the videos. Then, an improved DeepSort algorithm is used to track by detection. After tracking, the authors extract effective features from the tracked bounding box, use the output of the last convolutional layer, and introduce the attention weight factor into the tracking module for final fall event prediction. Finally, the authors use the sliding window for storing feature maps and SVM classifier to redetect fall events. The experimental results on the CityPersons dataset, Montreal fall dataset, and self-built dataset indicate that this approach has good performance in complex scenes. The pedestrian detection rate is 87.05%, the accuracy of fall event detection reaches 98.55%, and the delay is within 120 ms. [ABSTRACT FROM AUTHOR]

Scalar multiplications are considered an essential aspect of implementations of isogeny-based cryptography. The efficiency of scalar multiplication depends on the equation of the underlying elliptic curves and the addition chain employed. Bos and Friedberger recently stated that, for larger scalar multiplication, addition-subtraction chains will become more useful for twisted Edwards curves because of the differential restriction on Montgomery curves in the setting of isogeny-based cryptosystem. Motivated by these comments, we attempt to increase the efficiency of scalar multiplication in twisted Edwards curves in terms of the memory of algorithms. In this paper, we present a double-base addition-subtraction chain algorithm with memory efficiency for scalar multiplication. The memory usage of this part is O log n 2 / log log n , which is better than the result of the tree-based approach, which is O log n 2 . [ABSTRACT FROM AUTHOR]

In order to improve the retrieval efficiency and security of the cloud server, an encrypted cloud data mark and group search method (MGSM) based on singular value decomposition is proposed in this paper. Firstly, all documents are clustered, then indexes and query marks are constructed according to classes, and then documents with low correlation are filtered according to their matching degree. Secondly, the reserved document index vector is expressed as an index matrix, and the singular value decomposition (SVD) algorithm is employed to reduce the dimensionality of the matrix. Then, the corresponding threshold is set to improve the search efficiency while ensuring accuracy. Thirdly, the reduced-dimensional indexes are grouped to reduce the high-dimensional encryption key to multiple low-dimensional keys, further reducing the index encryption time. Theoretical analysis and experimental results show that the proposed method is more feasible and more effective than the compared schemes. [ABSTRACT FROM AUTHOR]

To a large extent, classical boosting denoising algorithms can improve denoising performance. However, these algorithms can only work well when the denoisers are linear. In this paper, we propose a boosting algorithm that can be used for a nonlinear denoiser. We further implement the proposed algorithm into a shrinkage curve learning denoising algorithm, which is a nonlinear denoiser. Concurrently, the convergence of the proposed algorithm is proved. Experimental results indicate that the proposed algorithm is effective and the dependence of the shrinkage curve learning denoising algorithm on training samples has improved. In addition, the proposed algorithm can achieve better performance in terms of visual quality and peak signal-to-noise ratio (PSNR). [ABSTRACT FROM AUTHOR]

This paper demonstrates an effective method of performing network reconfiguration (NR) and distributed generation placement (DGP) simultaneously called NR-DGP for the multi-goal function of reducing power loss and voltage deviation as well as enhancing load balance and feeder balance with the least number of changing switches. These membership goals are combined by the fuzzy decision-making relied on the max-min technique. The results for the NR and NR-DGP on two test system including of 33 and 84 nodes are gained by the improved moth swarm algorithm (IMSA). Wherein, IMSA is developed based on the original moth swarm algorithm (MSA) with improvement of the exploration mechanism using Lévy distribution. The calculated results show that NR-DGP method has gained the better improvement of the test systems' technical indicators than the NR only. The obtained results also show that IMSA has better performance for the NR and NR-DGP problems than the MSA in term the quality of the obtained optimal solution. Thus, IMSA can be an effective approach for determining the optimal solution of the NR and NR-DGP problems. [ABSTRACT FROM AUTHOR]

This article will focus on how to reduce the negative information in the main theme report. Negative information contains subjectivity, deviation, interference, and cancellation characteristics, which will influence the primary theme report's communication effect, interfere with the audience's interpretation of the report, and cancel out the report's positive energy. The original intention of the theme report is to promote social harmony and safeguard social justice, but the appearance of negative information makes the reported effect fail to reach the expected purpose. The concept of theme reports and negative information is defined in this work. This study examines the primary topic report's qualities, such as The Times' mainstream, good content, and strong report. In addition, the form and characteristics of negative information are also described. In this paper, a collaborative filtering recommendation method based on non-neighbor user contributions is suggested, which uses a linear fitting formula to apply the responsibilities of both neighbor and non-neighbor users to the recommendation system. The results show that the accuracy and diversity of our algorithm are better than those of traditional collaborative filtering algorithms. The diversity of several common recommendation algorithms is studied. The findings reveal that the diversity of recommendation algorithms is linked to the sparsity of data as well as the algorithm's suggestion mechanism. In general, the more scarce the data, the higher the recommendation algorithm's variety. At the same time, we also study the diversity of recommendation systems, and the results show that although the overall diversity of the system is gradually decreasing, user behavior is becoming more and more diverse. [ABSTRACT FROM AUTHOR]

In the current situation of university education in China, there are some problems that need to be solved urgently in college Chinese teaching in China, which seriously restrict the realization and implementation of college Chinese teaching objectives. The emergence and development of cloud computing technology can integrate different information media, and through the integration of traditional text, pictures, videos, and other resource media, it can be presented in a clearer and more vivid way. In this paper, a cloud computing resource scheduling model is established for the realization of the platform for the development and utilization of university Chinese cloud computing curriculum resources. The multi-QoS (Quality of Service) objective constraint problem is transformed into a single objective constraint solving problem. The improved GA (genetic algorithm) is used to solve the single objective constraint problem, and the square of the objective function is used as a fitness function, and a better resource allocation strategy is obtained. Experimental results show that the allocation time of the algorithm proposed in this paper is greatly reduced, and the QoS guarantee ability of cloud computing service providers is effectively improved. It has certain reference value for the further research of cloud computing technology in the development and utilization of college Chinese curriculum resources. [ABSTRACT FROM AUTHOR]

Multimodal biometrics fusion plays an important role in the field of biometrics. Therefore, this paper presents a multimodal biometrics fusion algorithm using deep reinforcement learning. In order to reduce the influence of user behavior, user's personal characteristics, and environmental light on image data quality, data preprocessing is realized through data transformation and single-mode biometric image region segmentation. A two-dimensional Gobar filter was used to analyze the texture of local sub-blocks, qualitatively describe the similarity between the filter and the sub-blocks and extract the phase information and local amplitude information of multimodal biometrics features. Deep reinforcement learning was used to construct the classifier of different modal biometrics, and the weighted sum fusion of different modal biometrics was implemented by fractional information. The multimodal biometrics fusion algorithm was designed. The Casia-iris-interval-v4 and NFBS datasets were used to test the performance of the proposed algorithm. The results show that the fused image quality is better, the feature extraction accuracy is between 84% and 93%, the average accuracy of feature classification is 97%, the multimodal biometric classification time is only 110 ms, the multimodal biometric fusion time is only 550 ms, the effect is good, and the practicability is strong. [ABSTRACT FROM AUTHOR]

In view of the poor effect of current sports dance movement detection, this paper puts forward a sports dance movement detection method based on posture recognition. By using the principle of posture recognition to obtain the characteristic information of sports dance movement, construct the action characteristic evaluation system, optimize the action detection algorithm combined with posture recognition technology, and realize the classified detection of sports dance movements. Finally, experiments show that the sports dance movement detection based on pose recognition has high practicability and effectiveness in the process of practical application and fully meets the research requirements. [ABSTRACT FROM AUTHOR]

In the process of wireless communication, the transmission of signals will be subject to various kinds of interference, which will affect the quality of communication. Interference detection is an important part of improving the reliability of communication. When the interfering signal has the same frequency as the original communication signal, with traditional methods, it is difficult to extract feature parameters. Aiming at this special cofrequency interference signal, this paper proposes a time series signal prediction model based on deep learning and uses the difference between the predicted signal and the received signal as the eigenvalue to detect interference. In order to improve the detection rate, the eigenvalues predicted by LSTM and Bi-LSTM networks are subjected to windowing experiments. The Support Vector Machine (SVM) is used to detect the interference of eigenvalues, and the comparison results are visualized by the confusion matrix. The experimental simulation results show that the Bi-LSTM model has better feature extraction ability for time series signals, and the prediction ability of the signal and the accuracy of interference detection are higher than those of the LSTM model. [ABSTRACT FROM AUTHOR]

The search range and search position of the particle are closely related to the shrinkage-expansion factor of the particle and the value of the center of the potential well. As the number of iterations increases, its search will gradually fall near the center of the potential well, and the search range will gradually decrease. Therefore, when the center of the potential well and the search range gradually approach the global optimum, the final result of the algorithm can be guaranteed to be the global optimum. Therefore, we need to optimize the shrinkage-expansion factor and the potential well center, improve the individual development ability of the group in the later stage of the algorithm and the expansion ability of the group, so that the potential well center is easier to fall near the global optimal point. Based on the chaotic strategy, a particle swarm initialization method is proposed. Using the unique ergodicity of the chaotic system, the method can make the particles spread well in the solution space of the search problem. Based on the antecedent normal cloud model, an adaptive method for determining control parameters and the center of the potential well is proposed. Based on the consequent normal cloud model, a particle adaptive mutation method is proposed. The comprehensive application of these improvement measures to the improved QPSO effectively improves the performance of the original algorithm. In this paper, the principle and method of multioptical axis parallelism measurement are studied. Based on the hardware equipment of the parallelism measurement system based on the large-diameter off-axis parabolic mirror collimator, the measurement accuracy and automation of the system are improved through image processing technology. The degree and anti-interference ability of the system are analyzed in detail. According to the characteristics of the system, an optimized focus evaluation function and a center positioning algorithm are proposed to improve the measurement speed and accuracy of the system. Through the improvement of the system DCT focus evaluation coefficient method and the optimization of the least squares ellipse fitting process, the measurement accuracy and anti-interference ability of the system are improved, the calculation time is shortened, and the real-time performance and automation of the system are enhanced. [ABSTRACT FROM AUTHOR]

The three-dimensional organic growth features of buildings have been given more and more attention according to the unique view representation regulations of the indoor construction industry, in order to optimize the usage and allocation efficiency of building space. To explore the configuration structure of building function space, the three-dimensional box dimension algorithm is used to measure the fractal dimension of the indoor and outdoor form of building space, and the two-dimensional and three-dimensional fractal characteristics of building space are compared and analyzed; the method of the second derivative is utilized for the automatic recognition of fractal scale-free areas, aiming at the imprecise problem of the artificial judgment of scale-free areas in earlier fractal research of interior and outdoor forms of architectural space. The experimental results show that the second derivative method can effectively and automatically identify the scale-free region. The coefficients of linear fitting are above 0.990, and the indoor and outdoor forms of architectural space have clear fractal characteristics. After applying the method, the three-dimensional fractal dimension grows, indicating that the interior and outdoor form usage of architectural space in this area is generally effective and compact. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the safety supervision of inland vessels. This paper especially aims at studying the vessel target detection and dynamic tracking algorithm based on computer vision and the target fusion algorithm based on multisensor. For the vessel video target detection and tracking, this paper analyzes the current widely used methods and theories. Additionally, facing the application scenarios and characteristics of inland vessels, a comprehensive vessel video target detection algorithm is proposed in this paper. It is combined with a three-frame difference method based on Canny edge detection and a background subtraction method based on mixed Gaussian background modeling. Besides, for the multisensor target fusion, the processing method of laser point cloud data and automatic identification system (AIS) data is analyzed in this paper. Based on the idea of fuzzy mathematics, this paper proposes a method for calculating the fuzzy correlation matrix with normal membership function, which realizes the fusion of vessel track features of laser point cloud data and AIS data under dynamic video correction. Finally, through this method, a set of vessel situation active intelligent perception systems based on multisensor fusion was developed. Experiments show that this method has better environmental applicability and detection accuracy than traditional manual detection and any single monitoring method. [ABSTRACT FROM AUTHOR]

With the rapid development and maturity of unconnected communication technology, effector technology, embedded computing technology, and distributed information processing technology, as well as the rapid advancement of digital processing and computing capabilities, unconnected effector Internet has received more and more attention. It is a new type of self-organizing unconnected multihop Internet. With the development and progress of technology and society, the development of unconnected effector Internet is also advancing by leaps and bounds, and it has a wide range of applications in many fields such as military, civil, environmental, medical, and industrial. At present, the research on unconnected effector Internet mainly focuses on the communication protocol, but there is almost no research on input review of unconnected effector Internet. Due to the limited energy of the effector and the limitation of the transmission signal bandwidth, the use of limited resources for input review research in effector Internet is of great significance to the development of unconnected effector Internet. Therefore, this paper studies the input review of unconnected effector Internet based on the L-A model on the on-chip embedded tune system. Because the classic low-power adaptive cluster layering protocol (LEACH) has the problems of unbalanced energy consumption and short node life cycle, this paper uses the embedded tune technology based on the L-A model and analyzes the remaining energy and location of the unconnected effector Internet node. Parameters are tested and studied. Through the research on the input review of unconnected effector Internet, the simulation results obtained show that the research in this paper is feasible and reasonable. [ABSTRACT FROM AUTHOR]

Accurate and stable cost forecasting of substation projects is of great significance to ensure the economic construction and sustainable operation of power engineering projects. In this paper, a forecasting model based on the improved least squares support vector machine (ILSSVM) optimized by wolf pack algorithm (WPA) is proposed to improve the accuracy and stability of the cost forecasting of substation projects. Firstly, the optimal features are selected through the data inconsistency rate (DIR), which helps reduce redundant input vectors. Secondly, the wolf pack algorithm is used to optimize the parameters of the improved least square support vector machine. Lastly, the cost forecasting method of WPA-DIR-ILSSVM is established. In this paper, 88 substation projects in different regions from 2015 to 2017 are chosen to conduct the training tests to verify the validity of the model. The results indicate that the new hybrid WPA-DIR-ILSSVM model presents better accuracy, robustness, and generality in cost forecasting of substation projects. [ABSTRACT FROM AUTHOR]

Aiming at the problem of low performance of crowd abnormal behavior detection caused by complex backgrounds and occlusions, this paper proposes a single-image crowd counting and abnormal behavior detection via multiscale GAN network. The proposed method firstly designed an embedded GAN module with a multibranch generator and a regional discriminator to initially generate crowd-density maps; and then our proposed multiscale GAN module is added to further strengthen the generalization ability of the model, which can effectively improve the accuracy and robustness of the prediction detection and counting. On the basis of single-image crowd counting, synthetic optical-flow feature descriptor is adopted to obtain the crowd motion trajectory, and the classification of abnormal behavior is finally implemented. The simulation results show that the proposed algorithm can significantly improve the accuracy and robustness of crowd counting and abnormal behavior detection in real complex scenarios compared with the existing mainstream algorithms, which is suitable for engineering applications. [ABSTRACT FROM AUTHOR]

In this paper, a fault-tolerant control system based on back-stepping integral sliding mode controller (BISMC) is designed and analyzed for both nonlinear translational and rotational subsystems of the quadrotor unmanned aerial vehicles (UAVs). The novelty of this paper is about combination of a classic controller with a repetitive algorithm to reduce the response time to actuator faults and have better tracking performance. The actuator fault is defined based on the loss of effectiveness and bias fault. Next, the iterative learning control algorithm (ILCA) is used to compensate for the unknown fault input according to previous recorded experiences. In the normal condition (without actuators fault), BISMC can force the actual trajectories toward the desired commands and reduce chattering about control signals, and in the presence of the actuators fault or external disturbances, the mentioned learning algorithm can incline the accuracy of the tracking performance and compensate for the occurred error. The Lyapunov theory illustrates that the proposed control strategy can stabilize the system despite the actuators' fault and external disturbances. The simulation results show the effectiveness of the proposed scheme in comparison with another method. [ABSTRACT FROM AUTHOR]

The characteristics of military equipment maintenance work are analyzed. According to the actual needs of the army, the optimization objective is designed, and a multiobjective flexible maintenance process optimization model is built based on the maintenance business organization process. Combining the advantages of NSGA-II algorithm and the simulated annealing algorithm, this paper proposes a novel improved HNSGSA algorithm, of which algorithm flow is detailed. In accordance with the requirements of the optimization model, this paper also specifically designs the coding methods of the process sequence, the equipment selection and the process scheduling, and the corresponding cross mutation method. The feasibility of the built model is verified by the actual data of maintenance business. And, the superiority, accuracy, and effectiveness of the proposed algorithm are further validated by the comparison with the NSGA-II algorithm and the simulated annealing algorithm, providing a scientific reference for the army to carry out equipment maintenance. [ABSTRACT FROM AUTHOR]

Failure mode and effect analysis (FMEA) is a systematic activity in the stage of product design and process design. However, the traditional FMEA has some shortcomings in practical application, such as too many evaluation languages, uncertain weights of influencing factors, and uncertain weights of evaluation members. This paper presents an FMEA evaluation method in manufacturing system based on similarity measure, nonlinear programming model, and intuitionistic fuzzy number (IFN). Firstly, the IFN is used to evaluate failure mode, which overcomes the defect of traditional FMEA evaluation value. Secondly, the weight of failure evaluation team members is solved according to the concept of similarity measure to make up for the blank of evaluation members' weight aiming at the shortage of unknown weight. Then, the definition of consensus measure is introduced to make the evaluators reach a consensus, and the weights of influencing factors of failure modes (FMs) are calculated. Finally, the weights of evaluators and influencing factors are calculated by IFN algorithm and score function, and the score value of each FM is obtained to rank instead of risk priority number (RPN). The objectivity and practicability of the new method are verified by the example of failure mode for an attractive electromagnet manufacturing system. [ABSTRACT FROM AUTHOR]

In recent years, the Internet of Things technology can effectively innovate applications and services. The Internet of Things technology has become more and more popular. It provides an effective and direct bridge between the physical world and virtual objects in cyberspace. With the increase in the intensity of dragon boat training and the increasingly fierce competition, the possibility of injury is increasing. Dragon boat racing is a noncontact team sport based on strength and technology. The purpose of this paper is to solve the problem of people's lack of understanding of the sports injuries and causes of dragon boat athletes. We used the data fusion algorithm and cluster maintenance optimization algorithm to study the application of Internet of Things technology in the cause of dragon boat sports injury. In order to save energy, extend the network life cycle, shorten service interruption time, and increase data packet transmission, the cluster maintenance optimization algorithm in this paper mainly improves and optimizes the startup time of cluster maintenance, which depends on the maintenance cost. The experiment result shows that the etiological detection system proposed in this paper matches the actual sports injury results well. The experiment result shows that the research on the cause of injury in dragon boat sports based on Internet of Things technology can detect the damage law well and can have a more comprehensive understanding for the cause of injury, which helps to prevent injuries better and take effective treatments. In the analysis part, it can be concluded that the detection system is very accurate in detecting the cause, and the accuracy rate is basically 100%. [ABSTRACT FROM AUTHOR]

According to the characteristics of traditional clothing, clothing identification is studied, and clothing identification and clothing culture learning are effectively combined to find a new method for the inheritance of national culture and strive to make contributions to the inheritance of national culture. According to the requirement of the traditional garment identification watermark monitoring system, a self-synchronous digital watermarking algorithm is designed and implemented. Watermark is embedded in the time domain, and feature information is extracted from traditional clothing by means of mean filtering and replaced by watermark to achieve the purpose of embedding information. Blind detection is realized without the participation of the original image. The difference between the traditional costume embedded with watermark and the original traditional costume is almost imperceptible. It can effectively resist synchronous attacks including clipping and time shifting, showing good robustness. Imperceptibility and robustness can be adjusted freely by embedding strength. The HOG + SVM algorithm is applied to minority clothing classification and recognition. By comparing different classifiers, it is concluded that the classifier trained by the support vector machine algorithm has the best classification effect on ethnic clothing. In order to improve the classification effect, the classical algorithm of color, texture, and shape feature extraction was combined with SVM to conduct experiments on the clothing database collected and sorted out in Yunnan ethnic minority communities, and finally, we verified that the HOG feature combined with the SVM classification algorithm achieved good results in the classification of ethnic clothing. [ABSTRACT FROM AUTHOR]

To address the problem that the accuracy of the SVM algorithm is affected by random parameters at the input end, a financial crisis early warning model (FCEWM) based on PSO-SVM is constructed based on the nonequilibrium sample characteristics of different financial conditions of listed companies in China's gem. The model uses the PSO algorithm to optimize the parameters of SVM and selects 24 financial risk evaluation indexes as the input to predict the financial crisis. The results show that the proposed model is superior to other models in prediction accuracy and robustness. [ABSTRACT FROM AUTHOR]

The commonly used method in network intrusion detection is abnormal behavior detection, but because abnormal behavior detection is based on artificially setting abnormal values for judgment, the efficiency is low and the false alarm rate is high. For this problem, an intrusion detection system architecture combining K-means algorithm and convolutional neural network algorithm has been introduced. First, the data stream is clustered through the K-means algorithm, and the abnormal data is initially separated, and then the data is applied to the convolution. In the neural network algorithm, the intrusion data flow is judged. The experimental results prove that the framework improves the efficiency of the intrusion detection system to a certain extent and effectively improves the detection accuracy. [ABSTRACT FROM AUTHOR]

To estimate and analyze the orbit of a spacecraft in the ascent phase, three algorithms are proposed in this paper: a two-satellite point-by-point intersection positioning algorithm, single-satellite positioning algorithm, and multiple-point intersection collaborative positioning algorithm. Meanwhile, two mathematic models of the spacecraft orbit are presented based on the kinematics characteristic and the least square method. Besides, by combining the results of the proposed satellite positioning algorithms with mathematic models of the spacecraft orbit, the particle filtering based on the Monte Carlo algorithm is applied to filtering of the final results of the spacecraft. Finally, the effectiveness of the two-satellite point-by-point intersection positioning algorithm and the single-satellite positioning algorithm is verified through the experiment simulation on the real data. [ABSTRACT FROM AUTHOR]

In this paper, the theory of viscoelastic material relaxation modulus testing, testing method, and material relaxation modulus parameter solution method is studied. Based on the IoT sensor test devices and the Hertzian mathematics theory, the relationship between the compression amount, pressure, and relaxation modulus of a rigid spherical indenter pressed into a flat viscoelastic material is studied. In combination with the Boltzmann superposition principle, the relaxation modulus test method and theory for viscoelastic materials are proposed. A good fitting curve was obtained to solve the relaxation modulus parameters of various materials under the three-element Maxwell model. The experimental setup and the results of the parameter fitting were analyzed to verify the feasibility and accuracy of the results. [ABSTRACT FROM AUTHOR]

Conventional ambiguity resolution (AR) strategy of directly fixing all raw frequency ambiguities for uncombined precise point positioning (PPP) generally requires a long initial time to ensure fixing reliability. The rich signals from multi-frequency GNSS can provide new opportunities for rapid PPP AR. In this paper, based on a unified multi-frequency uncombined PPP model, the raw frequency ambiguities are linearly transformed to the between-satellite-single-differenced extra-wide-lane (EWL), wide-lane (WL), and narrow-lane (NL) ambiguities, and a cascading ambiguity resolution (CAR) method of fixing EWL/WL/NL ambiguities sequentially is proposed. Meanwhile, a partial ambiguity fixing (PAF) strategy with ambiguity subset adaptively selected based on the successively increased elevations is also adopted in each step to improve the fixing rate. Further, experiments with globally distributed stations are carried out to verify the algorithm. With the constraints of EWL/WL AR, the precision of NL ambiguity and its variance-covariance matrix can be effectively optimized, so the time to first fix (TTFF) is significantly shortened, and the ratio value is also improved to varying degrees. As for BDS-only solution, the average TTFF is shortened from 23.7 min to 10.9 min, with an improvement over 50%; for GPS/BDS, GPS/Galileo, and GPS/Galileo/BDS combined solutions, the TTFF is shortened from 14.3 min, 9.4 min, and 6.7 min to 8.1 min, 2.6 min, and 1.8 min, which are, respectively, shortened by 43.4%, 72.3%, and 73.1%. In general, the proposed CAR strategy can shorten the TTFF of multi-GNSS multi-frequency PPP to about 2 min. The performance of EWL/WL/NL ambiguity-fixed solutions is also analyzed. The NL solution is generally at centimeter-level accuracy over the entire period; however, limited by the atmosphere errors during the convergence stage, the EWL/WL solutions can only obtain decimeter-level accuracy, and the difference between them and NL solution gradually decreases with the continuous improvement of atmosphere accuracy. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the subspace-like direction of arrival (DOA) estimation performs poor due to the error of sources number, this paper proposes a new super-resolution DOA estimation algorithm based on the diagonal-symmetric loading (DSL). Specifically, orthogonality principle of the minimum eigenvector of the specific covariance matrix and the source number estimation based on the improved K-means method were adopted to construct the spatial spectrum. Then, by considering the signal-to-interference-to-noise ratio (SINR), the theoretical basis for selecting parameters was given and verified by numerical experiment. To evaluate the effectiveness of the proposed algorithm, this paper compared it with the methods of minimum variance distortionless response (MVDR) and new signal subspace processing (NSSP). Experimental results prove that the proposed DSL has higher resolution and better estimation accuracy than the MVDR and NSSP. [ABSTRACT FROM AUTHOR]

Euler path is one of the most interesting and widely discussed topics in graph theory. An Euler path (or Euler trail) is a path that visits every edge of a graph exactly once. Similarly, an Euler circuit (or Euler cycle) is an Euler trail that starts and ends on the same node of a graph. A graph having Euler path is called Euler graph. While tracing Euler graph, one may halt at arbitrary nodes while some of its edges left unvisited. In this paper, we have proposed some precautionary steps that should be considered in exploring a deadlock-free Euler path, i.e., without being halted at any node. Simulation results show that our proposed approach improves the process of exploring the Euler path in an undirected connected graph without interruption. Furthermore, our proposed algorithm is complete for all types of undirected Eulerian graphs. The paper concludes with the proofs of the correctness of proposed algorithm and its computation complexity. [ABSTRACT FROM AUTHOR]

The foot-mounted pedestrian navigation system (PNS) that uses microelectromechanical systems (MEMS) inertial measurement units (IMUs) to track the person's position. However errors accumulate over time during inertial navigation solutions, which affects the positioning precision. In this paper, a multicondition zero velocity detector is used to detect the stance phase of gait. Then the errors are corrected in the stance phase and the swing phase, respectively, through the Kalman filter. When pedestrians are going up and down the stairs, the divergence of height will reduce the accuracy of three-dimensional positioning. In this paper, an accelerometer and a barometer are used to obtain altitude variation, and after that the stair condition detection (SCD) algorithm is proposed to correct the height of Kalman filter output and detect the walking state of pedestrians. Through theoretical research and field experiments, these algorithms are studied carefully. The results of the experiment show that the algorithm proposed in this paper can effectively eliminate errors and achieve more accurate positioning. [ABSTRACT FROM AUTHOR]

Counselling students remains a pre-eminence for most tertiary institutions in Ghana to the extent that institutions now have counselling units that extend to the departmental level. This study used the K-prototype machine learning algorithm to cluster students' behaviour based on 28 relevant attributes and further proposed a classification model. The analysis of the experimental outcomes using the elbow method reveals the formation of three distinct clusters with decreasing intra-cluster similarities and increasing inter-cluster distances. The first cluster uniquely consists of active learners with three or more roommates, primarily in the first year. The second cluster with the highest membership consists mainly of second-year students who exhibit passive classroom conduct and reside in a two-occupancy hostel. The third cluster contains a mixture of third and final-year students who are highly passive in class and live in a tenancy occupancy of two. After clustering, the K-nearest neighbours, logistic regression, naïve Bayes (NB), and AdaBoost ensemble algorithms were implemented to create a model for future learner cluster prediction. Simulation results using the tenfold cross-validation technique show that AdaBoost (NB) has the highest accuracy of 99.88% with an F-measure score of 0.999 and receiver operating characteristic–area under the curve value of 1.00. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet, various forms of network attack have emerged, so how to detect abnormal behavior effectively and to recognize their attack categories accurately have become an important research subject in the field of cyberspace security. Recently, many hot machine learning-based approaches are applied in the Intrusion Detection System (IDS) to construct a data-driven model. The methods are beneficial to reduce the time and cost of manual detection. However, the real-time network data contain an ocean of redundant terms and noises, and some existing intrusion detection technologies have lower accuracy and inadequate ability of feature extraction. In order to solve the above problems, this paper proposes an intrusion detection method based on the Decision Tree-Recursive Feature Elimination (DT-RFE) feature in ensemble learning. We firstly propose a data processing method by the Decision Tree-Based Recursive Elimination Algorithm to select features and to reduce the feature dimension. This method eliminates the redundant and uncorrelated data from the dataset to achieve better resource utilization and to reduce time complexity. In this paper, we use the Stacking ensemble learning algorithm by combining Decision Tree (DT) with Recursive Feature Elimination (RFE) methods. Finally, a series of comparison experiments by cross-validation on the KDD CUP 99 and NSL-KDD datasets indicate that the DT-RFE and Stacking-based approach can better improve the performance of the IDS, and the accuracy for all kinds of features is higher than 99%, except in the case of U2R accuracy, which is 98%. [ABSTRACT FROM AUTHOR]

Electronic component recognition plays an important role in industrial production, electronic manufacturing, and testing. In order to address the problem of the low recognition recall and accuracy of traditional image recognition technologies (such as principal component analysis (PCA) and support vector machine (SVM)), this paper selects multiple deep learning networks for testing and optimizes the SqueezeNet network. The paper then presents an electronic component recognition algorithm based on the Faster SqueezeNet network. This structure can reduce the size of network parameters and computational complexity without deteriorating the performance of the network. The results show that the proposed algorithm performs well, where the Receiver Operating Characteristic Curve (ROC) and Area Under the Curve (AUC), capacitor and inductor, reach 1.0. When the FPR is less than or equal 10 − 6 level, the TPR is greater than or equal to 0.99; its reasoning time is about 2.67 ms, achieving the industrial application level in terms of time consumption and performance. [ABSTRACT FROM AUTHOR]

Electronic component recognition plays an important role in industrial production, electronic manufacturing, and testing. In order to address the problem of the low recognition recall and accuracy of traditional image recognition technologies (such as principal component analysis (PCA) and support vector machine (SVM)), this paper selects multiple deep learning networks for testing and optimizes the SqueezeNet network. The paper then presents an electronic component recognition algorithm based on the Faster SqueezeNet network. This structure can reduce the size of network parameters and computational complexity without deteriorating the performance of the network. The results show that the proposed algorithm performs well, where the Receiver Operating Characteristic Curve (ROC) and Area Under the Curve (AUC), capacitor and inductor, reach 1.0. When the FPR is less than or equal 10 − 6 level, the TPR is greater than or equal to 0.99; its reasoning time is about 2.67 ms, achieving the industrial application level in terms of time consumption and performance. [ABSTRACT FROM AUTHOR]

In this paper, a new geometric structure of projective invariants is proposed. Compared with the traditional invariant calculation method based on 3D reconstruction, this method is comparable in the reliability of invariant calculation. According to this method, the only thing needed to find out is the geometric relationship between 3D points and 2D points, and the invariant can be obtained by using a single frame image. In the method based on 3D reconstruction, the basic matrix of two images is estimated first, and then, the 3D projective invariants are calculated according to the basic matrix. Therefore, in terms of algorithm complexity, the method proposed in this paper is superior to the traditional method. In this paper, we also study the projection transformation from a 3D point to a 2D point in space. According to this relationship, the geometric invariant relationships of other point structures can be easily derived, which have important applications in model-based object recognition. At the same time, the experimental results show that the eight-point structure invariants proposed in this paper can effectively describe the essential characteristics of the 3D structure of the target, without the influence of view, scaling, lighting, and other link factors, and have good stability and reliability. [ABSTRACT FROM AUTHOR]

Since cross-border e-commerce involves the export and import of commodities, it is affected by many policies and regulations, resulting in some special requirements for the recommendation system, which makes the traditional collaborative filtering recommendation algorithm less effective for the cross-border e-commerce recommendation system. To address this issue, a simple yet effective cross-border e-commerce personalized recommendation is proposed in this paper, which integrates fuzzy association rule and complex preference into a recommendation model. Under the constraint of fuzzy association rules, a hybrid recommendation model based on user complex preference features is constructed to mine user preference features, and personalized commodities recommendation is realized according to user behavior preference. Compared with the traditional recommendation algorithm, the improved algorithm reduces the impact of data sparsity. The experiment also verifies that the improved fuzzy association rule algorithm has a better recommendation effect than the existing state-of-the-art recommendation models. The recommendation system proposed in this paper has better generalization and has the performance to be applied to real-life scenarios. [ABSTRACT FROM AUTHOR]

In order to effectively enhance the low detection rates of dim and small targets caused by dynamic backgrounds, this paper proposes a detection algorithm for dim and small targets in sequence images based on spatiotemporal motion characteristics. With regard to the spatial domain, this paper proposes an improved anisotropic background filtering algorithm that makes full use of the gradient differences between the target and the background pixels in the eight directions of the spatial domain and selects the mean value of the three directions with the lowest diffusion function in the eight directions as the differential filter to obtain a differential image. Then, the paper proposes a directional energy correlation enhancement algorithm in the time domain. Finally, based on the above preprocessing operations, we construct a dim and small targets detection algorithm in sequence images with local motion characteristics, which achieves target detection by determining the number of occurrences of the target, the number of displacements, and the total cumulative area in these sequential images. Experiments show that the proposed detection algorithm in this paper can effectively improve the detection of dim and small targets in dynamic scenes. [ABSTRACT FROM AUTHOR]

Aiming at the problem of matching logistics service supply and demand, this paper proposes a two-sided matching decision model of logistics service supply and demand based on the uncertain preference ordinal. In this model, the uncertain preference ordinal information is first expressed by the interval numbers of the logistics service supply and demand, and it is converted into the satisfaction degree of supply and demand matching uncertainty expressed by the interval number. Then, a multiobjective optimal matching model is constructed based on the largest overall satisfaction of the logistics service supply and demand side and the smallest satisfaction variance of the supply- and demand-side individual, and the multiobjective solution algorithm is designed based on nondominated sorting genetic algorithm-III (NSGA-III). Interval numbers are used to sort the matching results to obtain the approximately optimal two-sided matching scheme. Finally, this paper verifies the correctness of the model and validity of the algorithm. [ABSTRACT FROM AUTHOR]

This paper considers an assembly scheduling problem which minimizes the total weighted tardiness. The system consists of multiple manufacturing machines in the first stage and an assembly machine in the second stage. A job is composed of multiple components, each component is manufactured on a dedicated machine in the first stage, and the assembly starts on the assembly machine after the completion of all the components' manufacturing in the first stage. This paper is to try to find effective and efficient schedules to minimize the total weighted tardiness of jobs. This paper analyzes some solution properties to improve search effectiveness and efficiency. Moreover, some lower-bound procedures are derived, and then four constructive heuristics and a branch-and-bound algorithm are suggested. The performances of the derived algorithms are evaluated through numerical experiments. For the problems with no more than 15 jobs, the branch-and-bound algorithm finds the optimal solutions within 20 minutes, and the performance of the four heuristics seems to be similar. However, for problems with more than 30 jobs, HWT shows the best performance among the four heuristics except for two machines. [ABSTRACT FROM AUTHOR]