Explore the vast range of titles available.

The cognitive radio network (CR) is a primary and promising technology to distribute the spectrum assignment to an unlicensed user (secondary users) which is not utilized by the licensed user (primary user).The cognitive radio network frames a reactive security policy to enhance the energy monitoring while using the CR network primary channels. The CR network has a good amount of energy capacity using battery resource and accesses the data communication via the time-slotted channel. The data communication with moderate energy-level utilization during transmission is a great challenge in CR network security monitoring, since intruders may often attack the network in reducing the energy level of the PU or SU. The framework used to secure the communication is using the discrete-time partially observed Markov decision process. This system proposes a modern data communication-secured scheme using private key encryption with the sensing results, and eclat algorithm has been proposed for energy detection and Byzantine attack prediction. The data communication is secured using the AES algorithm at the CR network, and the simulation provides the best effort-efficient energy usage and security.

The latest development trend of direct-drive electro-hydraulic servo technology is discussed. The working principle, system model and system control theory of an electro-hydraulic servo system are studied. The dynamic behavior of the direct-drive electro-hydraulic servo system is highly nonlinear, structure uncertainty. Considering that the standard PID controller cannot fulfill all the demands, it is necessary to use advanced means for compensation. A PID controller optimized by genetic algorithm for an electro-hydraulic servo system direct driven by a permanent magnet synchronous motor is proposed. The genetic algorithm is applied to optimize the parameters of the PID controller. The simulation and experiment research of one direct-drive electro-hydraulic servo system are carried out to verify the response properties of the proposed controller. The step signal tracking responses of the servo system with different parameters of PID controller are, respectively, reported. In addition, a feedforward PID controller using genetic algorithm optimization is also designed for the direct-drive servo system. The simulation and experiment results show that the feedforward PID controller using genetic algorithm optimization has good dynamic response characteristics in the electro-hydraulic servo system based on a direct-drive permanent magnet synchronous motor.

The neural machine translation model based on long short-term memory (LSTM) has become the mainstream in machine translation with its unique coding–decoding structure and semantic mining features. However, there are few studies on the Mongolian and Chinese neural machine translation combined with LSTM. This paper mainly studies the preprocessing of Mongolian and Chinese bilingual corpus and the construction of the LSTM model of Mongolian morpheme coding. In the corpus preprocessing stage, this paper presents a hybrid algorithm for the construction of word segmentation modules. The sequence that has not been annotated is treated semantically and labeled by a combination of gated recurrent unit and conditional random field. In order to learn more grammar and semantic knowledge from Mongolian corpus, in the model construction stage, this paper presents the LSTM neural network model based on morpheme coding to construct the encoder. This paper also constructs the LSTM neural network decoder to predict the Chinese decode. Experimental comparisons of sentences of different lengths according to the construction model show that the model has improved translation performance in dealing with long-term dependence problems.

In this paper, a new approach of automatic building for domain ontology based on machine learning algorithm is proposed, and by which the large-scale e-Gov ontology is built automatically. The advent of the knowledge graph era puts forward higher requirements for semantic search and analysis. Since traditional manual ontology construction requires the participation of domain experts in large-scale ontology construction, which will take time and considerable resources, and the ontology scale is also limited. The approach proposed in this paper not only makes up for the shortage of thesaurus description of the semantic relation between terms, but also takes advantage of the massive online encyclopedia knowledge and typical similarity algorithm in machine learning to fill the domain ontology automatically, so that the advantages of the two different knowledge sources are fully utilized and the system as a whole is gained. Ultimately, this may provide the foundation and support for the construction of knowledge graph and the semantic-oriented applications.

Fresh e-commerce cannot be separated from cold chain logistics as a guarantee when supplying fresh agricultural products in different places. On the one hand, the high cost of cold chain logistics requires the cold chain logistic enterprises to price their services provided by cold chain logistic enterprises. On the other hand, it requires fresh e-commerce to reprice their products considering cold chain logistic cost. Whether the pricing strategies of both are proper affects the income of both sides, and also affects the consumers’ willingness to pay. Based on Steinberg game model and benefit equilibrium analysis, a three-stage pricing model with third-party cold chain logistic enterprise as leader, fresh e-commerce company as follower and consumer as secondary follower is established. Through the analysis of cooperative game and non-cooperative game, the optimal pricing and the best income of the cold chain logistic enterprises and the fresh e-commerce enterprises in the process of using cold chain logistics are obtained. Taking two different types of fresh products as an example, this paper simulates two kinds of fresh products based on pricing model, compares the two strategies of cooperative game and non-cooperative game, probes into the change of profit between fresh e-commerce and cold chain enterprises in different price ranges and selects pricing strategy.

With the rapid development of big data and cloud computing, vehicular is connected to the Internet in the complex and uncertain driving environment. The rapid growth of the types of services used by vehicles has made the problem of inefficient of traditional driving environment architecture more and more obvious. The vehicle has to register and remember a large number of usernames and passwords to each server. Authentication schemes for multi-server architectures have been proposed and applied to a wide range of areas, but there has been little research on the Internet of vehicles. The long-term evolution for vehicle (LTE-V) is a wireless network architecture and can be used for cooperative communication in vehicular network. Communications and authentication for LTE-V have the high request in complex and uncertain driving environment. To meet the needs of complex and uncertain driving environments, this paper proposes a novel mutual authentication and the key agreement scheme (LEANDER) under multi-server architecture. In this scheme, elliptic curve is used to reduce the computational complexity, and a more concise authentication method is constructed. Random anonymity supports multi-server for two-way authentication and key agreement, so as to effectively protect the privacy of the vehicle. Moreover, it can be use BAN logic to prove and analyze the effectiveness of this scheme. The performance analysis results show that the proposed mutual authentication scheme is effective and more secure than other state-of-the-art methods.

The teaching–learning-based optimization (TLBO) algorithm is a new optimization technique that has been successfully applied in various optimization fields. However, the TLBO still has a slow convergence rate and difficulty exiting local optima. To overcome these shortcomings, a TLBO algorithm with a logarithmic spiral strategy and a triangular mutation rule (LNTLBO) is introduced. In the teacher phase, a logarithmic spiral strategy that enables students to approach the teacher is incorporated into the original search method to accelerate convergence speed. Meanwhile, a new learning mechanism with a triangular mutation is used to further enhance the abilities of exploration and exploitation in the learner phase. Thirteen unconstrained benchmarks and two constrained optimization problems are employed to examine the LNTLBO. The simulation results prove that the LNTLBO is efficient and useful for global optimization.

In recent years, data mining techniques have been widely applied in education. However, studies on analyzing the similarity or difference of the same learning pattern in different student groups are still rare. In this study, a data mining method which combines the concepts of contrast sets mining and association rules mining is introduced. It could provide quantitative analysis for the similarity and difference of association rules obtained from the academic records datasets of multiple grades. On this basis, student psychological features are deduced without being sensitive to privacy. The work in this study can help educators understand the learning and psychological states of students in different grades, so as to formulate teaching plans that are more targeted to improve their academic performance.

The similarities and differences between the K -means algorithm and the Canopy algorithm’s MapReduce implementation are described in detail, and the possibility of combining the two to design a better algorithm suitable for clustering analysis of large data sets is analyzed in this paper. Different from the previous literature’s improvement ideas for K -means algorithm, it proposes new ideas for sampling and analyzes the selection of relevant thresholds in this paper. Finally, it introduces the MapReduce implementation framework based on Canopy partitioning and filtering K -means algorithm and analyzes some pseudocode in this chapter. Finally, it briefly analyzes the time complexity of the algorithm in this paper.

The forecasting methods of water bloom in existence are hard to reflect nonlinear dynamic change in algal bloom formation mechanism, leading to poor forecasting accuracy of bloom. To solve this problem, this paper deeply analyzes the generation process of algal bloom, introduces the recursive time series algorithm into the deep belief network model and improves the model structure and training algorithm, and proposes a forecasting method based on the recursive timed deep belief network model. The model introduces the current moments and historical time values of the characterization factors and influencing factors at the input layer, and increases the connection between the input layer and the hidden layer of the deep belief network. A recursive algorithm is used to establish the relationship between the current time value of the characterization factor and the historical time value of the characterization factor, and the connection between the current time value of the hidden layer and the influencing factor is increased. By re-extracting the characteristics of the hidden layer at each moment, and then fine tuning the network parameters by the BP neural network, a recursive timing deep belief network model is finally constructed. The results show that compared with the existing forecasting methods, this method can extract the characteristics of time series data more accurately and completely to deal with the dynamic nonlinear process and can further improve the forecast accuracy of algal blooms.