Search

Wireless Sensor Networks (WSNs), as an important part of the Internet of Things (IoT), are widely deployed to the location estimation in WSNs. However, at present, the study of DV-Hop algorithm is still limited to the improvement of the sensor nodes in the ordinary region. In this paper, aiming at the complex areas under different application backgrounds, based on the analysis of the localisation principle of the traditional DV-Hop model based on optimisation algorithm, a dynamic weight positioning model based on genetic algorithm (DWMGA-DV-Hop) is proposed. The algorithm performs simulation experiments on three different types of test by adopting dynamic weight calculation model. And experimental results demonstrate that, under different test sets, compared with the standard DV-Hop algorithm, TW-PSODV-Hop and OCS-DV-Hop algorithm, this algorithm has the highest positioning accuracy and stability.

With the development of wireless sensor networks, and other information related high technologies, a lot of practical Internet of Things (IoT) applications have greatly increased the productivity. Currently, more and more capital is invested in IoT, especially intelligent agriculture as many countries begin to pay more attention to basic and intelligent agriculture. For a large intelligent agriculture system, it will cost a lot of time and energy for the mobile sink to collect all the data of the sensing system with the help of cluster head node. In this paper, we try to solve this issue by minimising the data collection path of the mobile sink, using the ant colony optimisation algorithm. We implement the algorithm in Python and conduct two experiments which show that we can get the best path of the given example and show how the efficiency changes when the numbers of ants and loops increase.

In order to predict the variation trend of ammonia (NH3) concentration accurately in piggery and reduce the risk of livestock breeding, a prediction model is established. Because NH3 has a great influence on the health of pigs, a prediction model can provide an effective way for pig industries to determine the environmental control strategy and take effective measures to evaluate the air quality of piggery. When predicted value of NH3 concentration is above the warning value, farmers can start fans in advance to maintain the health of pigs. The proposed NH3 concentration prediction model is based on Least Squares Support Vector Regression (LSSVR) model with Fruit Fly Optimisation Algorithm (FOA) to search the optimal parameters γ and σ of LSSVR. As the performances of LSSVR are greatly affected by the two parameters, three optimisation algorithms, Particle Swarm Optimisation (PSO) algorithm, Genetic Algorithm (GA) and traditional LSSVR, are used to compare with FOA. The calculated mean absolute percentage errors of the four prediction models are 0.81%, 2.95%, 4.04% and 5.92%, respectively. The prediction model is used in livestock breeding base, Zhenjiang City, China, and it performs well. The FOA-LSSVR prediction model can serve as an effective strategy applied in multivariable and non-linear piggery environmental control system.

Particle swarm optimisation with time-varying accelerator coefficients is a novel variant of particle swarm optimisation algorithm. Different from the standard version, the cognitive coefficient and social coefficient are both adjusting with the different generations to balance the exploitation and exploration capabilities. In this paper, particle swarm optimisation is incorporated into the methodology of DV-Hop algorithm to estimate the beacon nodes' positions. To show the performance, it is compared with other two algorithms, and simulation results show it is effective.

In this paper, an incorporated constrained differential evolution algorithm based on Invasive Weed Optimisation (IWCDE) had been proposed. The IWCDE algorithm is based on the standard differential evolution algorithm and incorporates the Invasive Weed Optimisation Algorithm. The IWCDE algorithm proposed the new mutation strategy and the strategy of 'Infeasible individual evolution'. The proposed algorithm was compared with several other evolutionary algorithms, the results showed that the proposed algorithm could overcome the premature convergence efficiently and had better global convergence and robustness. Finally, the paper established the optimisation model of parameter identification on machine joint surfaces, solved the problem by the IWCDE algorithm.

Ensuring urban security is an important public policy that the city government should provide, and efficient scheduling of emergency vehicles is an important measure to ensure urban security. This paper first combs the existing research literature, and expounds the main influencing factors of urban emergency vehicle scheduling and its problem characteristics. Then, an urban emergency vehicle scheduling model is constructed based on the entropy weight method, the timeliness, economy and safety are selected as key factors, and the improved path optimisation algorithm is employed to solve the model. Finally, an empirical analysis of emergency vehicle scheduling cases in the People's Square in S City is presented.

This paper proposes a new object classification method based on an improved bacterial foraging optimisation algorithm. Firstly, a dynamic step size is used instead of the fixed step size of the chemotaxis. Secondly, the fixed elimination-dispersal probability is replaced by the dynamic probability. Features are extracted to distinguish the objects, such as pedestrians, cars and pets. Ultimately, all the objects are classified using the improved bacterial foraging optimisation algorithm. The experimental results prove that the effectiveness of the object classification method proposed in this paper is better than that of other algorithms.

Artificial Bee Colony ABC is a recently proposed optimisation algorithm, which is inspired by the foraging behaviour of honey bees. Although the original ABC has obtained competitive performance on many optimisation problems, it lacks exploitation ability. To overcome this issue, an improved ABC algorithm called IABC is proposed in this paper. The IABC uses a new search strategy by incorporating some randomly selected individuals and the global best individual. In the experiment, a set of well-known benchmark functions are tested. Computational results show that the proposed IABC outperforms the original ABC and GABC.

Inspired by physical force, Artificial Physics Optimisation APO algorithm is a novel stochastic based on a physicomimetics framework. Driven by virtual force, a population of sample individuals searches for a global optimum in the problem space. The force law is a key problem associated with the performance of APO algorithm significantly. In the paper, an APO algorithm with the Feasibility and Dominance FAD method FAD-APO is employed to solve constrained optimisation problems. Three different force laws are constructed between the feasible individuals and infeasible individuals, which drive all individuals to search for a global optimum in the constrained problem space. Simulation results show that FAD3-APO algorithm may generally perform better than FAD1-APO and FAD2-APO; it is the most stable and effective among the three versions of FAD-APO algorithms. Meanwhile, a comparison with other population-based heuristics shows that the FAD-APO algorithm is competitive on some test function.

For logistics distribution route problem, this paper presents an improved genetic algorithm, combined with the thought of tree coded, to solve single vehicle logistics distribution route problem. The algorithm adopted Prufer array coding reducing three units length of chromosome, and the decoding method did not increase time complexity of chromosome decoded to calculate objective function value when compared with the traditional coding method which coded chromosome according to sequence traversing each node. In order to prevent the feasibility of solution being destructed by the traditional crossover and mutation operators, a single transposition operator and an ortho-position exchanging operator were also designed. The following cases show that the algorithm has a higher solving efficiency and is a great help to solve large-scale route optimisation problem.

Numerous problems in science and engineering can be converted into optimisation problems. Gravitational Search Algorithm GSA is a newly developed optimisation algorithm inspired by Newton's law of gravity and law of motion. However, the traditional GSA tends to suffer from trapping in local minima when solving complex problems. This paper proposes an enhanced gravitational search algorithm GOGSA, which utilises the generalised opposition-based learning to enhance the search ability. Experiments are conducted on 13 classical test functions. The experimental results and analysis demonstrate that GOGSA can obtain better performance on the majority of the test functions.

Firefly Algorithm FA is a new optimisation algorithm based on swarm intelligence, which has shown good performance on many optimisation problems. However, the standard FA easily falls into local minima because of too many attraction operations. To enhance the performance of the standard FA, a new FA is proposed in this paper. The new approach employs Generalised Opposition-Based Learning GOBL for population initialisation and generation jumping. To verify the performance of our approach, a set of benchmark functions tested in the experiments. Computational results show that the proposed approach obtains better performance than the standard FA and some recently proposed FA variants.

Swarm intelligent optimisation algorithms have been researched widely in recent years. Artificial Bee Colony ABC algorithm is a kind of swarm intelligent algorithm with briefness and efficiency for global optimisation problems. This paper focuses on the performance of ABC algorithm on the large-scale global optimisation problems. The algorithm has been tested on 12 benchmark functions from relevant literature. The experiment results of ABC algorithm on the large-scale global optimisation problems have been shown in this paper. The experiment results indicated that as the dimensions of the test functions increase, the performance of ABC on most test problems deteriorates gradually.

Particle Swarm Optimisation PSO is a population-based stochastic optimisation algorithm. The most important advantages of the PSO are that PSO is easy to implement and there are few parameters to adjust, but PSO is easy to get trapped in local optimum. In this paper, the premature convergence of standard PSO is investigated based on Markov chain. First, according to the difference model of standard PSO algorithm, the particle state sequence and swarm state sequence are defined and the one-step transition probability of state is introduced; it is shown that the particle state sequence and swarm state sequence are all Markov chains and their Markov properties are analysed. Second, for premature convergence of standard PSO, its analysis is given based on Markov chain. Last, it is proved that standard PSO is convergent to premature convergent state in probability.

To make up for the shortage of the dwMDSG algorithm on the positioning accuracy and convergence performance, this paper proposes a multidimensional scaling localisation algorithm based bacterial foraging optimisation. Firstly, MDS Multidimensional scaling algorithm is used to obtain the unknown nodes initial coordinates. Secondly, BFO bacterial foraging optimisation algorithm is adopted to obtain the unknown nodes final coordinates by optimising the local cost function. Experimental results show that the localisation accuracy, convergence and robustness of the proposed algorithm are better than that of the existing dwMDSG algorithm.

In order to ensure the safety in petrochemical production, it is of great importance for key equipment in petrochemical production unit to maintain, monitor and diagnose fault. Non-dimensional indicator is insensitive to the change of working condition so it is applicable to fault diagnosis technology, yet it is not satisfactory for complex concurrent fault diagnosis in rotating machinery and the number of conventional non-dimensional indicators is small. Building new non-dimensional indicator, which especially possesses the features of integrated diagnosis, is very significant to improve capability to diagnose fault. In the paper, the method of building new non-dimensional indicator is presented. Based on the previous research findings about 3MGCA to search arithmetical combination of conventional non-dimensional indicator, new non-dimensional indicator is acquired using optimisation algorithm of measured fault data. Experiments show that the proposed method is practical and efficient for building new non-dimensional indicator in rotating machinery, and it has good potential application in the engineering practice.

Data association is an essential part of track maintenance in multiple target tracking, which can be solved by multidimensional assignment methods. When there is a need to solve the multidimensional assignment problem, the ant colony optimisation ACO algorithm stands out as it can solve combinatorial optimisation problem with excellent performance in acceptable CPU time. Here, each measurement is modelled as an ant, each track is modelled as a city, and the problem of data association is modelled as the food locating by ants. Thus, a novel data association based on an improved ant colony optimisation algorithm ACODA is proposed in this paper. The detailed corresponding relationship and theoretical analysis between basic ACO algorithm and the ACODA algorithm are given. Simulation results show that as the number of targets increases, the ACODA algorithm performs better than JPDA and NN, with superior performance both in computational time and accuracy.

Based on the organisational behaviour theory and complex adaptive system method, the enterprise organisation behaviours are analysed for the firm dynamic growth evolution modelling. Further, the particle swarm optimisation algorithm is introduced to individual behaviour parameters optimising, so each individual can adjust their own behaviour parameters according to their own status and the surroundings, which makes agents more intelligent and adaptive than that in the previous research. Concretely, organisation behaviours in the firm are described at first. Then the firm growth evolution model is given and the group behaviour structure is also built up. Besides, the principles and evolution processes of the model are specifically presented and the firm growth evolution model is simulated. Finally, the simulation results are analysed in greater detail. The results illustrate that applying the particle swarm optimisation to the group behaviour has a strong guiding sense to the development of the enterprise.

k-Nearest Neighbour KNN is one of the most popular algorithms for pattern recognition and data classification, but the traditional KNN classification method has some disadvantages. In this paper, aim at the KNN classification method's limitation, we proposed a hybrid intelligent classification algorithm. This novel algorithm combined the particle swarm optimisation algorithm and weighted KNN algorithm to improve classification performance. The experimental results show that our proposed algorithm outperforms the traditional KNN method with greater accuracy.

Social Emotional Optimisation Algorithm (SEOA) is a recent proposed novel population-based optimisation technique inspired by the human behaviours. In human society, the emotion guides each individual to make decision so that his/her behaviour may provide some profits. However, due to the simple setting motion in the standard version, the emotion changes can not provide enough materials. Therefore, in this paper, a stochastic model is designed by adding Levy distribution. In this model, the emotion is changed with one Levy translation. Simulation results show the proposed method is effective and efficient when dealing with multi-modal famous benchmarks, especially for high-dimensional cases.

The optimal coverage problem plays an important role in wireless sensor networks. In this paper a new swarm intelligent technique, Social Emotional Optimisation Algorithm (SEOA), is used to solve the problem based on the probability measuring model. In SEOA, each individual represents a virtual person, and selects the behaviour according to the corresponding emotion index in each iteration. Simulation results showed that the effective coverage has reached 99.98%.