Search

A new hybrid direct/indirect adaptive fuzzy neural network (FNN) controller with state observer and supervisory controller for a class of uncertain nonlinear dynamic systems is developed in this paper. The hybrid adaptive FNN controller, the free parameters of which can be tuned on-line by observer-based output feedback control law and adaptive law, is a combination of direct and indirect adaptive FNN controllers. A weighting factor, which can be adjusted by the tradeoff between plant knowledge and control knowledge, is adopted to sum together the control efforts from indirect adaptive FNN controller and direct adaptive FNN controller. Furthermore, a supervisory controller is appended into the FNN controller to force the state to be within the constraint set. Therefore, if the FNN controller cannot maintain the stability, the supervisory controller starts working to guarantee stability. On the other hand, if the FNN controller works well, the supervisory controller will be deactivated. The overall adaptive scheme guarantees the global stability of the resulting closed-loop system in the sense that all signals involved are uniformly bounded. Two nonlinear systems, namely, inverted pendulum system and Chua's chaotic circuit, are fully illustrated to track sinusoidal signals. The resulting hybrid direct/indirect FNN control systems show better performances, i.e., tracking error and control effort can be made smaller and it is more flexible during the design process. Index Terms--Adaptive control, fuzzy neural networks (FNNs), nonlinear systems, state observer, supervisory control.

Interval type-2 fuzzy logic systems (IT2FLSs) have better abilities to cope with uncertainties in many applications. One major drawback of IT2FLSs is the high computational cost of the iterative Karnik-Mendel (KM) algorithms in type-reduction (TR). From the practical point of view, this prevents using IT2FLS in real-world applications. To address this issue, a novel non-iterative method called Moradi-Zirkohi-Lin (MZL) TR method is proposed for computing the centroid of an IT2FLS. This makes the practical implementation of the IT2FLSs simpler. Comparative simulation results show that the proposed method outperforms the KM TR method in terms of computational burden. Besides, closer results, in terms of accuracy, to the KM TR method among the existing non-iterative TR methods are also achieved by the proposed TR method. [ABSTRACT FROM AUTHOR]

Pot seedling transplanting is the main way of vegetable planting, there were some problems of labor intensity and low level of automation in the process of mechanized transplanting of vegetable pot seedling. Aiming at this problem, this paper designed an intelligent transplanting system for vegetable pot seedling, which included the function of the seeding storage mechanism, the seedling feeding mechanism, the ejecting seedling mechanism, the pinch mechanism and the planting mechanism, the system monitors the whole movement process of planting through pressure sensing, stroke detection and limit switch, obtains each planting stage of the seedlings during planting, and uses the CCD camera to identify the key steps of planting and seedlings to determine whether it is missing. Three broccoli seedlings with different moisture content and the age of 42d were used as the experimental object of seedlings planting experiment. Results indicated that: Under the conditions of meeting the agronomic requirements of vegetable pot seedlings, when the speed of picking-up seedlings was 75 seedlings per minute, which resulted in a 95% success rate of picking-up seedlings and 5% leaked seedlings rate, the planting effect of vegetable pot seedlings was the best. The research can provide useful reference for the development of intelligent transplanting technology of vegetable pot seedling. [ABSTRACT FROM AUTHOR]

Controlled switching strategy can reduce overvoltages due to UHV transmission line closing. However, the traditional method is difficult to determine the quantitative relationship between the closing performance of circuit breakers and the risk of failure of transmission lines. Based on the risk of failure data calculated by the statistical method, an adaptive network-based fuzzy inference system (ANFIS) model for forecasting risk of failure that occurs during the closing of transmission lines is presented. An ANFIS model is employed to map the closing performance of circuit breakers and the risk of failure of the UHV transmission line. The model is based on a system of fuzzy-rules written on the basis of previous results, the knowledge and experience. The fuzzication of input variables is carried out using fuzzy sets with the Gauss membership functions. "Grid partition" was used to generate the fuzzy inference system, and a hybrid learning rule was used to optimize the fuzzy system parameters. After the appropriate model is established through training and checking, it can forecast the risk of failure in different closing performance of circuit breakers. Then, it is easy to analyze the closing performance of circuit breakers in different risk of failure requirements. [ABSTRACT FROM AUTHOR]

In this paper, under the circumstance of uncertain customer demand, the enterprises on the same node in multiple supply chains conduct horizontal inventory coordination according to their own inventory and demand. Based on the combination of horizontal inventory replenishment and vertical normal replenishment, the related mathematical model has been established. By studying the inventory strategy in the decentralized and centralized decision-making, the dual marginalization effects are found in the network system composed of multiple supply chain. So the revenue sharing contract is introduced to solve this problem. It has been found in the study that after adopting the horizontal inventory coordination mechanism of the supply chain, the profit of the members in the supply chain system and the overall profit of the system are both higher than those which didn't adopt the mechanism. The improved multi-objective genetic algorithm is used to calculate and verify the problem. In particular, after the revenue sharing contract is adopted, the profits are further enhanced. [ABSTRACT FROM AUTHOR]

The occupational health and safety problems caused by indoor dust and toxic gases in industrial plants are becoming increasingly serious. Vertical push-pull ventilation can effectively control dust and toxic gases and avoid indoor environmental pollution. The velocity of the air supply hood and exhaust hood in the push-pull ventilation intelligent device directly affects the control effect of the dust and toxic gases. However, no scholar has given a reasonable ratio of the air supply and exhaust velocity of the vertical push-pull ventilation device. Therefore, this paper uses the combination of Fluent numerical simulation technology and smoke visualization experiment to explore the best ratio of the air supply and exhaust velocity in the push-pull ventilation flow field. The research shows that the traces of the wind flow obtained by numerical analysis under different k which is the ratio of the air supply and exhaust velocity is consistent with the traces of visualized smoke in the actual experiment; The optimal ratio of air supply and exhaust is k = 1.75, which can effectively guarantee the indoor environment, occupational health and work efficiency of the operators. [ABSTRACT FROM AUTHOR]

In Guangxi marine soft foundation of a highway, the research of the intelligent dynamic response of marine roadbeds under traffic loading is carried out. To describe the interaction characteristics of vehicles and soft marine foundation, fine-analyzing the mechanical mechanism of various kinds of damage in early stage and the key factors affecting on the car, it need step up pavement coupling. Accordingly, it was based on the assumption of rigid pavement based on the Lagrange method, meet the viscoelastic foundation of the infinite beam, using sine wave road model of MW. Sayers vehicle road coupling system is used to calculate and analyze the time history curve of traffic load. Then, plugged the loads into that the finite element, the initial dynamic stress and the counting of the influence of marine soft foundation depth was obtained under traffic loading. The results show that the vehicle road coupling system based on the balance mechanics method is effective. It can be extended to consider the stress of traffic loads and ocean soft foundation, and calculate the depth, considering the viscoelastic boundary. It effectively predicts the stress of marine soft soil foundation, and has important guiding significance for theoretical research and engineering practice. [ABSTRACT FROM AUTHOR]

In this paper, in the so-called centralized charging and unified distribution mode, a two-stage optimization model is proposed for capacity planning and ordered discharging strategies of centralized charging stations considering the peak-shaving effects. Firstly, the operating states of battery pack are analyzed at each moment by combining with distribution modes, then the first stage planning is processed, that is, by taking the numbers of battery pack and generators as the control variables, the mathematical model aiming at minimizing the construction cost of centralized charging stations can be solved by Simulated Annealing Particle Swarm Optimization (SAPSO). Next, in the second stage planning, in order to maximize the peaking effect of the centralized charging station, the cost function aiming at minimizing load variance is proposed, and the discharge power of each time can be obtained by using yalmip toolbox. Finally, simulation results are provided to verify the effectiveness and usefulness of the proposed optimization model. [ABSTRACT FROM AUTHOR]

This paper reprocesses the information of the boundary intelligent contour so as to effectively extract the codes of image contour features. The algorithm based on the coordinates of contour extracted through the level set evolution algorithm is used to obtain several 2D contour matrixes with the same size after repeated conversions. Moreover, the matrixes are diagonally, column-wise and horizontally coded to obtain new coded features. The anti-interference analysis of algorithm indicates that the algorithm of extracting feature code has variable and flexible extraction schemes and high stability. Distinguishable information can be obtained in similar images more easily. In order to prove the validity of the proposed algorithm, feature code exaction algorithm is used to facial expression recognition, and a facial expression recognition model on the basis of facial part contour code exaction is established. According to the experimental results, this facial expression recognition system can eliminate the interference with recognition resulted from the similarity of samples. The comprehensive recognition rate of facial expression is up to 97.20%. [ABSTRACT FROM AUTHOR]

With the rapid development of clinical and laboratory medicine, the field of bioinformatics boasts of extensive clinical records and research literature. Retrieving effective information from this huge data has become a challenging task. Hence, Intelligent text summarization, which enables users to find and understand relevant source texts more quickly and effortlessly, becomes a very significant and valuable field of research. In this study, we propose an improved TextRank algorithm with weight calculation based on sentence graph to solve this problem. For the experimental dataset obtained from Pubmed, we represent terms as vectors by using Skip-gram model. We design three methods which utilize word embeddings to calculate weights between sentences. Then we build an undirected graph with sentences as nodes. At last, we use the improved TextRank algorithm to calculate the importance of sentences and further generated summarizations base on its ranking. The experimental results and analysis on the datasets demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

We shall consider intelligent homological dimensions of 0-direct union of finite Rees matrix semigroups. First we give some characterizations of Rees matrix semigroup algebras. Then if K is a ring and S has a Rees matrix ideal M, we give the bounds of r.gl.dim K[S] in terms of r.gl.dim K [Ti] and r.gl.dim K[S/M]. The bounds for r.gl.dim K[S] are given, supposing that the finite monoid S is a 0-direct union of some finite Rees matrix semigroups which are in forms of Si = M (Ti ; Ii ; Λi ; Pi). In addition, it is determined that K[S] has finite homological dimension if and only if each Ti has finite homological dimension. [ABSTRACT FROM AUTHOR]

The efficiency of the supply chain of pig breeding in China is low due to the structure of scattering raising-households and the competition among the enterprises within the supply chain is also fierce. Faced with the uncertainty of the market environment and the complexity of the decision-making environment, how to choose the competitive strategy and competition mode for pig breeding enterprises and determine the optimal sales price and sales volume is the key problem to be solved by enterprises in the supply chain management. Based on this, this paper constructs a model of competition between two manufacturers (large farmers) and two retailers (pork wholesalers) in the pig breeding industry under fuzzy environment. Under the three modes of Cournot competition, Collusion competition and Stackelberg competition, the competition model between two retailers is constructed in turn, and the optimal strategy of each manufacturer and retailer is obtained. Finally, the mental state index is introduced to describe the decision maker's attitude or preference to the risk, which can make the model more reasonable. The result shows that the change of the mental state index will not only influence the optimal solution, but also affect the final decision result. [ABSTRACT FROM AUTHOR]

As there are many uncertain factors in the geological hazard risk, great challenges are brought to the comprehensive evaluation of it. In order to improve the comprehensiveness and accuracy of geological hazard risk assessment, a cloud fuzzy clustering algorithm is constructed in this paper, which can effectively estimate and evaluate uncertain variables. The weight value of the risk cloud droplets is calculated as the input. By setting up clustering conditions and function output conditions, the cluster weights of the inputs which meet requirements can be obtained by multiple clustering iterations. Through the introduction of time parameters, the influence of time factors on data importance and the risk severity of geological disaster emergencies are fully considered. The experimental results show that the calculated risk degree cluster weights are less than 1, which verifies the feasibility and practicability of the algorithm. The research in this paper shows that the clustering dynamic assessment of geological hazards can help to improve the accuracy of risk assessment and provide reference and help for the prevention and control of regional geological hazards. [ABSTRACT FROM AUTHOR]

Stock market trading is relatively difficult due to the relatively complicated investment in financial markets. In order to solve this problem, an industry configuration model based on deep learning network sentiment mining and fundamental research is proposed innovatively in this paper. Firstly, by crawling the network information, the network public opinion data is used to conduct industry classification and sentiment analysis on the data, thereby obtaining the industry sentiment index and the industry income forecast. Then combined with the fundamental data and market data and the technical indicators generated by it, multi-factor analysis is carried out, and the income forecast is obtained. Through three sets of comparative experiments, the results show that the investment returns obtained are the best with the industry configuration model based on deep learning-based network sentiment mining and fundamental research. [ABSTRACT FROM AUTHOR]

There are still many problems in the application of face recognition technology in specific environments. In order to improve the recognition accuracy of face recognition technology in large-scale event scenes, a face tracking algorithm is constructed based on improved ORB features in this paper. The algorithm uses the kernel function color histogram to model the target, which can perform well on target recognition during rotation or edge occlusion. The value of the face representation function is calculated by combining the texture feature and the color feature. By converting the function value into moment feature and combining it with the Bhattacharyya coefficient, the tracking performance of the target and the accurate detection of the target real scale improves. Taking the Tianjin National Games as an example, the intelligent security system based on face recognition was designed and implemented. The test results show that the proposed algorithm can reduce the face feature dimension effectively. When the control library is no more than 10,000 people, the false alarm rate is 1%, and the false negative rate is less than 5%. It provides a new recognition method for face recognition in the application of large-scale event scenes. [ABSTRACT FROM AUTHOR]

Measurement matrix is an important link which has important influence on signal sampling and reconstruction algorithm. Although the traditional random measurement matrix has good effect in reconstruction signal, the hardware implementation is difficult and it requires a lot of storage space. LDPC codes has a sparse check matrix with low density and strong orthogonality. When the RIP conditions are satisfied, the columns and rows are not correlated. In view of the problems existing in the measurement matrix, the deterministic measurement matrix based on the sparsity of photograph LDPC codes is constructed in this paper. Each submatrix is obtained through the circular shift of other submatrices, which is easy to be implemented on hardware. Experimental results show that the sparse matrix performance of LDPC codes is improved in PSNR and dNMSE compared to the traditional methods by using the same orthogonal matching pursuit (OMP) algorithm for optimization and the same compression ratio. At the same time, it consumes less time in the reconstruction of remote sensing image, and the running speed is greatly improved, which can meet the real-time demand, it also provides an effective measurement matrix construction method for the practical application of compressed sensing theory. [ABSTRACT FROM AUTHOR]

How to recommend learning resources to users accurately to meet the individual needs of users becomes the key issue with the increasing number of online education users. A personalized recommendation system was proposed in this paper based on user preference behavior data analysis to analyze the online education recommendation model. It determines the criteria set of the recommendation system with the product attribute mining method, and then uses the personalized recommendation algorithm for user preference modeling to explore the user's preference for each criterion, thereby producing more accurate recommendations. The simulation results of the algorithm proposed in this paper show that the multi-criteria recommendation algorithm using user distance similarity works best. Using this personalized recommendation algorithm based on user preference can effectively improve the recommendation quality. [ABSTRACT FROM AUTHOR]

There are many optional basic frameworks of the Internet of Things, which result in high energy consumption for Internet of Things monitoring platform of straw recycling, and cannot improve the thermal energy conversion rate of the straw recycling monitoring system effectively. Thus, the design is based on smart surveillance system of Internet of things of straw recycling process. The WMNBM14s chip and the STM32F103 chip are used in the basic frame of Internet of things to collect and process the straw recycling data in the monitoring system, and obtain the data processing result of the straw recycling process. The data processing result of the straw recycling process is transmitted to Internet of Things Control Terminal through the BCM43362 wireless chip. The experimental results show that the designed platform has low energy consumption and can improve the thermal energy conversion rate of the straw recovery system. [ABSTRACT FROM AUTHOR]

There are various kinds of common natural disasters, including flood, drought, typhoon, geological disaster, forest fire and major biological disaster. Natural disaster is an abnormal event in the evolution of geographical environment, but it has become one of the most important natural factors hindering the development of human society. With the economic development and population expansion of human beings, water resource shortage is becoming more and more serious, so drought has always been a major natural disaster faced by mankind. This paper studies the GIS-based risk assessment and regionalization of Taihang Mountain drought and flood disasters. In the process of regional environmental quality assessment, GIS technology is used to conduct an objective and comprehensive evaluation of the environmental quality of the whole region. This paper then constructs the combination of GIS technology and QUEST algorithm. Based on the decision tree model of Taihang Mountain drought disaster risk assessment, the risk of drought disaster in Taihang Mountain is evaluated. The results show that the distribution of drought disaster in Taihang Mountains is similar to that of drought disaster risk. The risk of drought disaster mainly distributes in the middle and west of Taihang Mountains. The risk in the east of Taihang Mountains is the lowest. The risk in the west of Taihang Mountains increases gradually. Generally speaking, the drought resistance of southern Taihang Mountains is higher than that of northern Taihang Mountains. [ABSTRACT FROM AUTHOR]

In order to pre-warning the product quality risk of the e-commerce platform, this paper studies the machine learning algorithm for the products quality risk assessment, which propose the Fuzzy C-Means clustering algorithm for the feature extraction and the Cost Sensitive Leaning (CSL)-Naive Bayesian algorithm to construct the assessment model for E-commerce product quality risk form the massive and unbalanced data. The experimental results show that the Machine Learning algorithm based on Spark has better scalability and superiority in the large-scale data environment, which can accurately identify e-commerce product quality risk. [ABSTRACT FROM AUTHOR]

People can rely on complex tactile systems to perceive the basic physical properties of an object, and take the corresponding action and pressure to grab the object. However, this task is not easy for mechanical manipulator. The feedback of most manipulators is limited to pressure, it is difficult for manipulators to identify the other properties of the object by touch. A new manipulator method is designed in this paper. The tactile images are reflected by flexible tactile sensor in this manipulator system. A large number of tactile images are used to build training set by which the capsule network is trained to evaluate images. When an object is captured by a manipulator, and parameters such as shape, rigidity, weight and density of target objects are analyzed. Pseudo color transformation of tactile images is performed, in this way, the changes of each parameter of tactile signals can be observed visibly. It is innovative to process the tactile image by using capsule network and realize the evolutionary bionic tactile function. [ABSTRACT FROM AUTHOR]

To deal with the problem of unbalanced load and ignoring task priority in previous task scheduling algorithms, this paper proposes a task scheduling algorithm named P-Min-Min-Max, which combines with priority and greedy strategy. Under the condition of considering the task priority, the algorithm leverages the execution time of tasks for greedy strategy, and binding large task and small task in the task list to form "task pair" to perform scheduling, so as to effectively solve the problem of unbalanced load. To reduce the average response time of tasks, the algorithm priority schedules the small task from the "task pair". The experimental results show that, compared with the Min-Min and P-Min-Min algorithm, the proposed algorithm improves the system resource utilization and service quality of user, and saves the total execution time for tasks. Compared with Max-Min and P-Max-Min algorithm, the proposed algorithm improves the system resource utilization and service quality of user, and reduces the total completion time and average response time. [ABSTRACT FROM AUTHOR]

In the current agricultural product consumption market, the consumer's demand for agricultural products tends to be diversified and individualized, and they need stricter links of cold chain logistics distribution of agricultural products. The cold chain logistics of fresh agricultural products is also the business of high energy consumption and high carbon emission in the logistics industry. The contradictory relationship between it and the "low-carbon economy" advocated today leads to the necessity to consider the relationship between economic benefit and environmental impact in the process of rapid development. Based on this, this paper, from the perspective of low-carbon economy, based on the analysis of the necessity of optimizing the distribution path of cold chain logistics of agricultural products, constructs a model for this and puts forward a swarm intelligence optimization algorithm-particle swarm optimization (PSO) algorithm. The algorithm is improved from inertia weight, convergence factor, learning factor, and population size and so on. The optimized PSO algorithm is compared with the traditional PSO algorithm. Finally, the simulation results show that the improved algorithm can be used to optimize the distribution path of cold chain logistics of agricultural products effectively, and the specific optimization countermeasures are put forward according to the actual situation. [ABSTRACT FROM AUTHOR]