Intelligent Algorithm

The artificial neural network [26] is a kind of adaptive system, which is composed of many neurons and used to abstractly simplify and simulate human brain activity. The artificial neuron as shown in Fig. 2.4 can be used as a simple processor that can deal with the arrival signals by weighted sum as  

In practice, a nonlinear function with no memory is usually defined as an activation function to change the output of neurons. 

The choice of activation function depends on its application object in the mixed intelligent algorithm. In Chap. 6 of the book, we use Sigmoid function  

Neural network has been widely used in fields of function approximation, pattern recognition, image dealing, artificial intelligence, optimization and so on [26, 102]. Multilayer feed forward artificial neural network is a major type of the neural network which is connected by input layer, one or more output layers and hidden layers in a forward way. Each layer is composed of many artificial neurons. The output of previous layer neurons is the input of the next layer as shown in Fig. 2.6. 

The multi-layer forward artificial neural network was firstly proposed by Minsky and Papert [103]. Cybenko [104] and Hornik et al. [105] have proved that multilayer forward networks with any munber of neurons of the ixia hidden layer can be close to any Borel continuous function. Moreover, if there are infinite neurons in the hidden layer, only one network of forward neurons is needed to approximate to any continuous function with arbitrary precision. So the multi-layer forward nemal network has been widely applied in function approximation [106]. 

---

We saw in chapter 1 that Artificial Intelligence algorithms incorporate a memory. In the ANN the memory of the system is stored in the connection weights, but in the SOM the links are inactive and the vector of weights at each node provides the memory. This vector is of the same length as the dimensionality of points in the dataset (Figure 3.6). 

In the case of the ESTMS-MS data, actual amino acid sequence can be deduced. This is possible due to the CID processes, which breaks the peptides further into amino acid ions. Each amino acid ion has a specific mass and by calculating masses of specific amino acid from the MS spectra, the exact sequence of the peptide and in turn the protein can be deduced. The workhorse of such analysis is a program called Sequest . Since the ESTMS-MS analysis provides information about the actual amino acid sequence, it is also useful to obtain information about protein modifications (such as phosphorylation) and toxicant-induced protein adducts. This has become even easier with the advent of new software tools and highly intelligent algorithms such as SALSA . 

Fig 2. The use of intelligent algorithms with standard bulk parameter monitoring equipment allows for a robust system that is capable of triggering on and classifying a wide diversity of threat agents including unknown events. 

Artificial intelligence algorithms have also been embedded in docking codes, notably ant colony optimization (AGO) and particle swarm optimization (PSO) [80,... 

The advantage of LP methods for extracting spectroscopic information from spectra is exploited by Haselgrove and Elliott who developed a computer intelligence algorithm which is able to analyze a large quantity of data based on a user-defined pattern of expected components. 

This chapter is organized as follows. Sections 5.2 and 5.3 concentrate on the process of risk mitigation, with a focus on the short period of time after an earthquake. Section 5.4 describes the modification of an artificial intelligence algorithm. A search, in order to find safe post-disaster routes for the intervention teams. Section 5.5 presents the results of the case studies and Sect. 5.6 contains the conclusions of our work. 

There are several technical challenges in this kind of system. First, miniaturized actuation modules of swallowable size must be designed. Second, intelligent algorithms must be developed to enable the real-time triggering of the therapeutic treatment when needed. Third, robust transmission of massive data from inside the body to the body surface must be available, which requires specially designed antermas that can penetrate well through... 

In the third part, we design a hybrid intelligent algorithm to solve the model by combining stochastic simulation and genetic algorithm. 

Next we will design a hybrid intelligent algorithm based on stochastic simulation to solve this model. 

The hybrid intelligence algorithm process is shown in Fig. 4.2, and the steps are shown in details as below. 

The termination is decided by termination of maximum algebra max gen. If thybrid intelligence algorithm process (in Sect. 4.3.3). If t = max gen, stop the algorithm. The maximum fitness value and its corresponding individual of the population in the total iterative process are recorded. 

In the hybrid intelligent algorithm, population size = 100, crossover probability Pc = 0.6, mutation probability = 0.5, number of iterations Gmax = 20,000, rank-based evaluation function a = 0.05 and there are 3000 random simulation. The main frequency of the PC for calculating is 2400 MHz, and all the algorithm program is realized by C++ language. 

To further verify the validity of the algorithm and the random expected value model, we simulate different values of parameters of hybrid intelligent algorithm ... 

In the hybrid intelligent algorithm, set population size N = 130, crossover probability p = 0.4, mutation probability = 0.5, number of iterations... 

---