Swarm Intelligence Research Papers

Introduction to Computational Mathematics (2nd Edition, 2015)

This is the 2nd Edition of the best-selling book "Introduction to Computational Mathematics".

descriptionView Paper arrow_downwardDownload

DEVELOPING UNDERSTANDING OF A CITY POPULATION IN LOCAL GOVERNMENT: A CASE STUDY IN ORGANISATIONAL LEARNING

This research, conducted by the author when a Senior Researcher at Newcastle University, UK, was funded by a UK governance organisation to help them assess, integrate and improve their understanding of the governed population.... more

This research, conducted by the author when a Senior Researcher at Newcastle University, UK, was funded by a UK governance organisation to help them assess, integrate and improve their understanding of the governed population.

ABSTRACT: Governance organisations have been urged to develop more holistic evidence-based approaches with partners to better deal with issues affecting the governed population. This presupposes an understanding of the population, yet there has been little research work addressing how governance organisations come to understand their governed population, nor how this understanding can be improved upon within such organisations.

This case study examined in-depth how understanding of a governed population was developed within one UK local governance organisation and it explored how such understanding might be developed and improved through more holistic and evidence-based organisational learning within the organisation and its governance partnerships.

The research methodology involved placement within the governance organisation, participant observations on several projects and innovative initiatives, observations within, across, and outside the organisation, and also interviews with varied key stakeholders.

The study examined:

- stakeholder engagement and networks
- current and varied understandings of the population
- mechanisms actually used for developing understandings
- the influence of context on organisational learning

and analysed these to arrive at a recommendations to improve organisational understanding of the governed population.

In the case studied, significant strengths were found: including innovative past learning trials for development, extensive ongoing networking activities, and many varied and accumulating quantitative datasets available across partnerships.

However, entrenched organisational approaches and practices constrained the development of holistic evidence-based understanding, for instance: the absence of systematic maintained collective learning processes; weak recording and forgetting of understandings; methodological exclusion of stakeholders from the development of understanding; the relative neglect of qualitative data, explanations, investigations, interpretations, and reflexivity; and also implicit organisational acceptance of such limitations and low aspirations.

Nonetheless, untapped opportunities existed to enable change including: latent practitioner knowledge and innovative management champions, the desire for improvement and raised aspirations within learning networks, and the development potential of alterative learning approaches.

It was concluded that more holistic evidence-based understanding was possible, but required new learning approaches beyond those then in use in both local government or academia.

Recommendations are made to utilise and develop improved organisational learning approaches trialed and reported in the case study.

It is argued that the case study findings, conclusions, and recommendations may be applicable to other similar local governance organisations and partnerships that seek to better understand local populations, services and interventions.

The work was also submitted for, and awarded, an MPhil (at Newcastle University, supervised by Prof. Patsy Healy)

descriptionView Paper arrow_downwardDownload

Book: Theory and New Applications of Swarm Intelligence

by Rafael Stubs Parpinelli

2012

The field of research that studies the emergent collective intelligence of self-organized and decentralized simple agents is referred to as Swarm Intelligence. It is based on social behavior that can be observed in nature, such as flocks... more

Another important aspect is the necessity to set synchronization barriers. A barrier forces a thread to wait until all other threads of the same block reach the barrier. It helps to guarantee the correctness of the algorithm running on the GPU, but it can reduce the time performance. Furthermore, threads within a block can cooperate among themselves by sharing data through some shared memory and must synchronize their execution to coordinate the memory accesses (see Fig. 1). Although the GPUs are famous because of their

The NVIDIA CUDA platform classify the NVIDIA GPUs using what they call Compute Capability as depicted in NVIDIA (2010b). The cards with double-precision floating-point numbers have Compute Capability 1.3 or 2.x. The cards with 2.x Capability can run up to 1,024 threads in a block and has 48 KB of shared memory space. The other ones only can execute 512 threads and have 16 KB of shared memory space.

Analyzing the convergence of the fitness values, the results for the parallel FSS versions on the GPU demonstrate that there are no reduction on the quality performance over the original version running on the CPU. Furthermore, there is a slight improvement in the quality of the values found for the Rastrigin function (see Fig. 4), specially for the asynchronous FSS version B. It might occurs because the outdated data generated by the race condition can avoid premature convergence to local minima in multimodal problems. Fig. 3. Rosenbrock’s fitness convergence as a function of the number of iterations.

Fig. 5. Griewank’s fitness convergence as a function of the number of iterations. According to these results, all FSS implementations based on the GPU achieved a time performance around 6 times better than the CPU version.

Fig. 4. Rastrigin’s fitness convergence as a function of the number of iterations. Analysis of the Performance of the Fish School Search Algorithm Running in Graphic Processing Units

‘ig. 1. Illustration of Probability Density Function for Gauss Distribution

Fig. 1. Family of estimating PSO methods Until now, many researchers have paid much attention to the issue, i.e. effectually obtaining the PSO with high search performance, and proposed a number of advanced algorithms to deal with it. These endeavors can be basically divided into two approaches: manual estimation and mechanical estimation shown in Figure 1.

As genetic operations in the RGA/E, roulette wheel selection, BLX-« crossover, random mutation, non-redundant strategy, and elitism strategy are used for efficiently finding an optimal individual (i.e. an optimal PSO) from the population of parameter values of the PSO. On being detailed, further refer to (33).

Fig. 3. Comparison of two pairs of the used fitness functions As an example, Figure 3 illustrates the relative evaluation between two pairs of the criteria, {(4,), 3+ and {F,,F,}, during the evolutionary computation. It is clearly observed that the properties of the instantaneous fitness functions, g(q,) and g,, are quite different. Namely, while the change of g(q,) is monotonous increment, the change of g, is non-monotonous increment with violent stochastic vibration. In contrast to this, the criteria, F, and F,, are all monotonous increment with a minute vibration. Because both F, and F, are the sum of instantaneous fitness functions, g(q,) and %,, over time-step, in theory, their variance is inversely proportional to the interval of summation. Thus, they could lead to vastly inhibit noise which comes from dynamic evaluation to the estimation. This property indicates that which of both F, and F, is well suitable for evaluating the search performance of the PSO, regardless of the difference in objects of evaluation themselves.

Fig. 4. Fitness functions corresponding to the given benchmark problems in two-dimensional space. (a) The Sphere problem, (b) The Griewank problem, (c) The Rastrigin problem, (d) The Rosenbrock problem. Figure 4 illustrates the distribution of each fitness function in two-dimensional space. It is clearly shown that the properties of each problem, i.e. the Sphere problem is an unimodal with axes-symmetry, the Rosenbrock problem is an unimodal with axes-asymmetry, and the Griewank and Rastrigin problems are multimodal with different distribution density and axes-symmetry.

Theory and New Applications of Swarm Intelligence

Clans are groups of individuals united by a kinship and each clan has at least one guide. Inspired by these leadership characteristics, Carvalho and Bastos-Filho (Carvalho & Bastos-Filho, 2009a) proposed a topology called Clan PSO. Asa part of the topology, each clan is composed by particles which are connected to the other particles of the same clan in order to share information quickly, as shown in the example depicted in Figure 2. The algorithm has two phases executed in every iteration, the delegation of the leaders and the conference of the leaders. In previous works, Carvalho and Bastos-Filho (Carvalho & Bastos-Filho, 2009a) recommended to use just some few clans in order to avoid extra overhead within the iteration. More details about them are given in the following subsections. 3. Clan PSO

After the Delegation, the leaders of each clan are selected and a new virtual swarm is composed by them. A PSO with the leaders can be ran using global (Figure 4(a)) or local (Figure 4(b)) topology. The former induces a faster convergence, while the latter allows more exploitation.

At each iteration, each clan singly performs an independent PSO and the particle that obtainec the best position within the clan is delegated as a leader of the clan in the iteration. Figure ‘ illustrates an example with the leader delegated in each clan.

Volitive PSO is a hybridization of the FSS and the PSO algorithms and it was proposed by (Cavalcanti-Junior et al., 2011). The algorithm uses two FSS operators in the Inertia PSO, the feeding and the collective-volitive movement. Each particle becomes a weighted particle, where the weights are used to define the collective-volitive movement, resulting in an expansion or contraction of the school. As a results, the Volitive PSO presents good features of the PSO and the FSS to tackle dynamic problems. These features are, respectively, fast convergence and the capacity to self-regulate the granularity of the search by using the volitive operator. Figure 5 illustrates the features aggregated in the Volitive PSO.

Fig. 9. Box plot of Volitive Clan PSO 3x18 in the last iteration in high severity environment.

Fig. 1. Iustration of neighbourhood topologies from [Mendes et al., 2004]: Fully connected (All), Ring, Four clusters, Pyramid and Square. where x,,(t) is the ith component of the position of the particle i and v,;(t) the ith component of its velocity; p,, is the iz, component of the best position ever visited by the ith particle; 9); is the im component of the best position ever visited by the neighbourhood of the particle; ais called inertia weight, it is used to control the impact of the previous history of velocity on the current one; 1 and r2 are uniformly distributed random numbers between 0 and 1; ci and cz are positive acceleration constants. The formula (4) is used for each dimension of the objective function, for each particle and synchronously at time step for all the particles of the swarm.

Abscissa (m) of the used sensors function to the metrology set

Fig. 4. Half truss structure with its loads; Elpeam and Elcotumn are the unknown parameters.

Fig. 6. FE model of the physical model with the main beam bearing on SB and the wood plate. A 3D finite element model, 3DFEM, presents the global experience fig. 6. This 3DFEM helps to estimate the equivalent stiffnesses of the elastic support of the main beam considering the association of the stiffnesses of the SB and the plate as a Winkler spring of which stiffness by support is unknown. The fig. 7 gives the displacements measured during the experimental tests for each support set (illustrated by the points), whereas the displacements obtained with 3DFEM for each support set is illustrated by the continuous curve. The good correlation between measurements and simulations confirms the good quality of the 3DFEM model and justifies both a priory estimation of the equivalent stiffness by support and the imits of the space research using for the PSO.

Fig. 8. Localisation of the sensors used in both numerical and physical models.

Table 2. Abscissa of the sensors used during the real experience.

The average value of each unknown parameter is very close to the reference but the standard deviation in not zero, which means that all solutions are not identical, even in this perfect case. Some scatter due to the meta-heuristic algorithm affects the identification process. However this scatter remains small. In real cases, it will be overshadowed by other error sources that will be studied now. Table 6. Statistical analysis of the identified parameters using exact field data, structure 1, metrology set CMi.

Table 8. Statistical analysis of the identified parameters using noised field data, structure 3. he studied structure is here the structure 2, STR2, ie. the half truss structure presented at ection 3.1.1. Let us assume that one must identify the Young Modulus E, the inertia of the olumn I-olumn and the inertia of the beam, Ibeam. Four different levels of noise on field data € = 0% (perfect data), then ¢ = 1%, 3% and 5%) are considered and simulations are epeated 20 times. The results are presented in Figures 1land 12and Table 8.The first result s that one obtains a front of solutions, since it is not possible to uncouple the weight of E rom that of inertia: for the same product Elj, there exists an infinite number of acceptable airs {E, I; = (El))/E = k/E} satisfying the same criteria. In order to estimate the sensitivity of he identified parameters to the field data, the sensibility of the displacement to stiffnesses vas calculated. Elcotumn Or Elbeam are varied in the [-50%; +50%] range and the displacement s calculated on 3 points of the beam, and on three points of the column, cf. fig. 4. Only lisplacements perpendicular to the main axis of the element are calculated.

Fig. 10. Illustration of the noise on field data and the dispersion of identified parameters k,, Structure 1, CM}.

The results confirm that only some field data are sensitive to the stiffness variations. The stiffness variation of the column inertia (reversely beam) has only a negligible influence on beam (reversely column) displacements. Thus, during the identification process, the magnitude of the errors on sensors localized on the beam will not impact the column because a lack of sensibility, and reversely. A more detailed analysis Table 9 shows that sensitivity of column displacement to column parameters is slightly larger than the same for the beam. The sensitivity has been calculated as the ratio between the variation of the displacements at the studied point with the variation of the stiffness. Those results show that the displacements of the column are more sensitive to a variation of the stiffness of the column that for the beam and explain why the scatter of the identified stiffnesses Elcolumnfig.12 is more important that the scatter of the identified stiffnesses Elbeam. Indeed,

Fig. 12. Inertia and Young Modulus identified, structure 2, noised with € = 3%. when field data on the column are noised, the inertia of the column to identified have to be badly identified from the reference value regards the magnitude of the noise. That result focuses how chosen of both the nature and the localisation of the field data regards the parameters to identified is important on the accuracy of the identification process.

We will illustrate the multi-objective particle swarm optimization for the design of a wood- plastic composite decking with three objectives [Michaud et al, 2009]. In this example, the optimization focuses on the creep, swelling, and exhaustion of abiotic resources functions. The design variables are mainly characteristics of raw materials such as timber particle sizes and chemical or thermal timber changes.

Fig. 14. The influence graph of relationships between the decision variables and the objectives. with an intermediate value calculated at 0.69 (partially oriented) - see Michaud et al, op.cit., whereas the other variables used in the equations (12), (13) and (14) are continuous. In fact the def function (equation 12), in its developed formula has an algorithm form due to the conditions on the discrete kcran.

Fig. 15. Solution space of the multi-objective (def, SW and efr) optimization problem determined from a MOPSO of 1000 generations of 30 particles. The equations (5) and (8) are used as position updating rule of respectively real and discrete variables. The equation (4) is used as velocity updating rule for all variables. During the optimization process, the real variables converge to their optima according to the objective functions, whereas each discrete variable randomly traverses its space of definition and consequently its best solution is identified. Due to the discrete variables, the solution space of the multi-objective optimization problem is discontinuous (fig. 15)

Fig. 17. Stability of the Pareto front: a) constant number of particles, b) constant number of iterations [Ndiaye et al., 2009]. Theory and New Applications of Swarm Intelligence

‘he number of MOPSO solutions on composite formulations depends on the ratios between he components and their desired precision. The number of solutions grows in function with he precision of ratios between the components using a logarithm-like law. It starts at 1500 olutions for a precision of 2 (the lowest possible precision) to more than 5000 for a precision reater than 5 (fig.18). The matrix ratio in composite formulation generates a peak of olutions around 75% for any precision of ratio. This large number of solutions makes them lifficult to handle. One solution is to take into account, in the system process, the user of the ystem so he could fix the precision of ratios, and for each ratio, its desired range; the latter eing included in the domain of validity of the variable representative of the ratio. For xample if you want to formulate a wood-plastic composite with a matrix ratio lying etween 30% and 40% without biopolymer, it is sufficient to restrict the range of the variable epresentative of the matrix ratio (Am) between 0.3 and 0.4 and the one representative of the iopolymer ratio in matrix component (@pio) between 0.0 and 0.0. In this case the number of olutions in the Pareto front fall down to 20.

PUCHY NWIELa-PICUloue AIQOTUTTT for Training the Radial Basis Function Network for Data Classification and Disease Diagnosis final outputs of network in the output layer. The input layer of this network has m units for m dimensional input vectors. The input units are fully connected to I hidden layer units, which are in turn fully connected to the J output layer units, where J is the number of output layer. Each neuron of the hidden layer has a parameter mean vector called center. Figure 1 shows the detailed structure of an RBF network. Each input data x with m dimensions, x= (X1,X9,...,X,,), are located in the input layer, which broadcast to hidden layer. The hidden layer has J neurons and each neuron compute the distance between the centers and the inputs. Each activation function of the neuron in hidden layer is chosen to be Gaussians and is characterized by their mean vectors c;and its spread parameter @; (i=1,2,...,]). That is, the activation function ¢(x) of the i hidden unit for an input vector x is given by:

where the weight matrix is represented as W and the ¢ matrix is the H matrix, respectively. The GD algorithm can be implemented to minimize the MSE term defined as the equation (3) based on the following equations. GD is the derivative based optimization algorithm (Karayiannis, 1999)that is used to search for the local minimum of a function. The algorithm takes steps proportional to negative of the gradient of function at the current situation with given the parameters a; and assumed all £; are equal to 0. In general, the output of a RBF network can be written in the following form.

Fig. 3. The mean square error versus complexity of the classification of the Iris dataset. Generally speaking, the complexity of trained RBF network with a large number of hidden nodes is larger but its corresponding mean square error is smaller. In experiments, The Figs. 3-7 recorded the mean square error and complexity of each trained RBF network based the Eq. (23) and (24). These figures clearly appear the phenomenon that the GD is the worst because of the largest mean square error with the same complexity among all algorithms.

Fig. 5. The mean square error versus complexity of the Glass classification.

Figure 3 shows the relationship between the complexity and mean square error in training the RBF networks of Iris dataset. These figures appear that the results of PSO, ABC and FF are superior to the GD. The Fig. 4 show the results of ABC and FF algorithm are superior to the results of GD and PSO in the training the RBF networks for Wine dataset. The Fig. 5 show the best is the result designed by PSO algorithm. The Fig. 7 demonstrates the best are the usages of the FF, however, the results of GD, PSO, ABC and FF do not clearly differentiate form the results of Fig. 6.

Fig. 7. The mean square error v.s. complexity of the WDBC classification. Theory and New Applications of Swarm Intelligence

Theory and New Applications of Swarm Intelligence Fig. 1. Representative genes selected by our algorithm from 100 runs for the BC dataset. (A) A heatmap representation of the most frequent genes. Darker (red) or lighter (green) colors represent higher or lower expression respectively. Ord represents the order of genes given by frequency in 100 models (shown in parenthesis). (B) Class centroid for each gene. Negative values represent under-expression relative to a common reference.

to increase from the initial value of size. The smallest average accuracy was 95% for size=5 but tending for model sizes around 8, which was limited by the m parameter used. This suggests that the decrease in accuracy is due to the low number of features used. This is sensible because the number of classes for LY dataset is 5, so, the use of 8 features is a compromise between high accuracy at low number of features. Overall, these results show that our implementation is able to control the number of active features and support our proposal that a high number of features for accurate classification of functional genomics data is not necessary.

Fig. 3. Initialization tests for the BC (A-B) and LY (C-D) datasets. (A-C) Accuracy evolution. (B-D) Dynamics of the number of active features. Points as in Figure 2. The runs presented above, which changed all parameters coordinately, show the overall behavior for different settings. However, the effects of each adaptation are not well appreciated. Therefore, we tested each adaptation separately. To challenge the initialization adaptation, we varied b from 5 to 400 setting b={5,10,25,50,100,400} while other parameters were kept fixed (u=10, e=1, n=2, m=600). Results are shown in Figure 3. For the BC dataset (Figure 3 A-B), accuracy was clearly smaller for b=400 within the first 50 epochs. On the other hand, for the LY dataset the accuracy was higher for larger values of b (Figure 3 C-D). For both BC and LY datasets, the final number of active features decreased when b decreased. Such decrease would be beneficial for our purposes since potential biomarker

models would become more compact. Nevertheless, when initialization was smaller than update (b =5) for the BC dataset, the number of active features increases. This increase was also observed in LY for b <= 20. For the BC dataset a trend for around 10 active features is clearly observed even for b =400. In this case, it took 600 epochs to decrease the number of active features from 400 to less than 20 and to reach the same level of accuracy than in the other runs. The decrease in the number of features and the poor accuracy for runs with high b suggest that the number of active features is excessive. This may happen when the classifier is overloaded with noisy features. On the other hand, for the LY dataset, the number of active features does not decrease systematically such as that in the BC dataset. Presumably due to high accuracies in LY that are already close to 1 (the maximum possible value); thus no major evolutive pressure is present. Overall, runs tend to adjust the number of active features depending on the starting point and the accuracy pressure.

Under-Updated Particle Swarm Optimization for Small Feature Selection Subsets from Large-Scale Dataset

Table 4. Distribution of the number of active features, from 5 to 15, in runs at different values of n and m for the BC dataset. The highest frequency is shown in bold.

Fig. 7. (A) Top genes found in 100,000 runs for the BC dataset. Inset: Comparison of feature selection frequency for 10,000 and 90,000 runs. (B) Generation of the negative dataset and positive added features. Features were sorted by the number of times they were found in the best particle for 100,000 runs. Top 494 were removed to generate the negative dataset. Top features were then injected progressively to the negative dataset: first 10, then 20, 50, 100, 200, 300, 400 and 494 (from leftmost dashed line to rightmost dashed line). We consider that this value is very conservative since we used raw p-values uncorrected for multiple tests. The number of features whose frequency surpasses this value was 494. Consequently the negative datasets carried 2,426 features. The number of 100,000 was chosen in order to be confident that the rank of top genes would not change among different runs. Indeed ranks between two runs of 10,000 and 90,000 have no major differences (see Figure 7A inset). If our algorithm cannot find related features in this negative dataset, a decrease in the final accuracy would be expected. As projected, the mean accuracy in 1000 runs for the negative dataset was 72% (labeled with BOTTOM in Figure 7B) while the same indicator in the original dataset was 82% (labeled with FULL in Figure 8B). Then, we inserted only the original top 10 features to the negative dataset (representing 0.4% of the 2,436 total features) and counted how many times the same top 10 features were found in the best models for 1000 runs. We also performed this procedure for top 20, 50, 100, 200, 300, 400 and 494 originally removed features. Results are shown in Figure 8A. We found that the high accuracy is easily restored after the first insertion (labeled TOP10 in Figure 8B). However, results show that the next 10 features were needed to fully restore the original observed accuracy distribution (labeled TOP20 in Figure 8B). We found all 10 and 20 top inserted features and more than 90% among the top 100 injected features. These results indicate that most frequent features (and presumably those more related to classes) are easily found even in highly noisy scenarios (99.6% of noisy features). Nevertheless, search efficiency was decreased to 60% when 494 top features were added. Within this, top 50 features were always found. Therefore, the search capability was uncertain only for those features ranked in the order of hundreds, presumably, because of random effects.

Fig. 8. (A) Search efficiency in the top added features. (B) Fitness distribution for uuPSC search capability tests. We then asked about the amount of information that uuPSO is able to find in the original dataset. That is, the improvement attributed to the uuPSO. For this, we generated random models of equal sizes than those observed in the models generated for the negative dataset. These models would represent the amount of information (given by accuracy) found by random chance. Similarly, we generated series of 20 random models recording only the best in each series. These would represent the best models that drive the search at the beginning of the swarm optimization procedure. Results show that the baseline for the amount of information is about 54% given by random models in the negative dataset (labeled with Random in Figure 9B). The accuracy distribution from the best of the random series indicates that uuPSO starts with 66% accuracy (labeled with Best Random in Figure 8B), which is then improved to 72% during the uuPSO process (labeled with BOTTOM in Figure 8B). Overall, these results show that the average improvement by uuPSO in the BC dataset is 16% (from 66% to 82%) when good predictors are present.

this case, were have maintained the synchronization barriers only in the functions used to update the positions and evaluate the barycenter. The pseudocode of the Asynchronous FSS - Version A is shown in algorithm 2. In the second approach, called Asynchronous - Version B, all the synchronization barriers were removed from the code in order to have a full asynchronous version. The pseudocode of the Asynchronous FSS - Version B is shown in algorithm 3.

5. Simulation setup and results The FSS versions detailed in the previous section were implemented on the CUDA Platform. In this section we present the simulations executed in order to evaluate the fitness performance of these different approaches. We also focused on the analysis of the execution time. Theory and New Applications of Swarm Intelligence

In all these experiments we have used a combination of individual and volitive steps at both initial and final limits with a percentage of the function search space Bastos-Filho et al. (2009). Table 2 presents the used parameters for the steps (individual and volitive). Three We used a 1296 MHz GeForce GTX 280 with 240 Processing Cores to run the GPU-based FSS algorithms. All simulations were performed using 30 fish and we run 50 trial to evaluate the average fitness. All schools were randomly initialized in an area far from the optimal solution in every dimension. This allows a fair convergence analysis between the algorithms. All the random numbers needed by the FSS algorithm running on GPU were generated by a normal distribution using the proposal depicted in Bastos-Filho et al. (2010).

Table 4. The Average Value and Standard Deviation of the Fitness value at the 10,000 iteration for Rosenbrock function.

Social Emotional Optimization Algorithm with Random Emotional Selection Strategy

Table 2. Estimated appropriate values of parameters in the PSO, cumulative fitness values, and frequencies in the top-twenty optimizers. The PSO in a-type: Cy) = 0, ¢; = 0, €y > 0; The PSO in b-type: €, = 0, ¢; > 0, 6 > 0; The PSO in c-type: ¢y > 0, ¢, = 0, €, > 0; in d-type: €) > 0,¢, > 0,é, > 0. The symbol ”-” signifies no result corresponding to contain type of the PSO. Theory and New Applications of Swarm Intelligence

Table 5. Estimated appropriate values of parameters in the PSO, criterion values and frequencies in the top-twentv optimizers. The PSO in d-tvne: 6. > 0.4, > 0.6, > 0. Theory and New Applications of Swarm Intelligence below.

(b) High severity with initialization of 50% o! particles.

Table 5. Identified equivalent stiffnesses using sensors from set B. Table 4. Identified equivalent stiffnesses using sensors from set A. 3.3 Sources of errors impacting the accuracy of the identification process: Synthetic experience Concerning synthetic experience, the following works relies on either numerical using the finite element (FE) software Castem©, or analytical model.

stiffnesses were correctly identified but the identified parameters show slight variations for each of the 20 simulations. The results are presented in Table 6.

Table 10. Variables X = {x1, x2, ..., X12} related to the composite formulation. see table 10 for the meaning of other variables. Water swelling function (SW)

Table 5. The used datasets in this study Table 4. The used parameters of Firefly algorithm

Table 1. The used parameters of GA PUCHY WIReLa-TICUlouG AUIQOTUTTT for Training the Radial Basis Function Network for Data Classification and Disease Diagnosis

Table 6. The average PCC and standard deviation results of the Iris dataset using different algorithm. One of the most important issues of designing the RBF network is the number of neurons in the hidden layer. Thus, we implement the RBF networks which have 1 neuron to 8 neurons for comparison, and each dataset is running 10 times based on 4-flod cross-validation. The average percentage and the corresponding standard derivation defined as the Eq. (25) of the designed RBF network by different algorithms are listed in Tables 6-10.

Table 7. Statistical average PCC results of the Wine dataset using different algorithms

Table 8. Statistical average PCC results of the Glass dataset using different algorithms. PICHy MeClta-MeurlsuC AIQOMUINT! for Training the Radial Basis Function Network for Data Classification and Disease Diagnosis

Table 10. Statistical average results of the WDBC dataset using different algorithms.

Table 11. Area under curve (AUC) of ROC analysis of RBF network with eight hidden nodes. (The best results are highlighted in bold)

In this paper we focused on the selection of small subsets of features from large-scale datasets. In this context, we mainly used two datasets generated using microarray data from breast cancer and leukemia that had been previously reported and studied in a similar fashion (Trevino and Falciani, 2006). For comparison with other PSO algorithms, we also used other three datasets in order to show overall effects and the generality of our adaptations (see Table 1).

Table 2. Comparison of PSO algorithms: the accuracy (Acc) and number of feature (size) of the best model found among 100 runs is shown in best-model columns. accuracy is the number of correctly predicted samples divided by the total. The mean and standard deviation (SD) of the accuracy and number of features were estimated from the resulted models (100 in most runs). Compared to uuPSO, all model accuracies and number of features were significant using a Wilcoxon rank sum test at p < 0.0005 except those marked with ¢ where p > 0.05. time was estimated for the 100 runs. A star (*) marks times estimated from partial results where at least 20 runs have finished. This estimated time should not be largely affected since run-time standard deviation is low. For example, for the ovarian dataset the standard deviation per run was 0.138 and 0.696 hours for sbPSO and Wang PSO respectively. The accuracy using all features is shown in column “All Acc” for comparison. Xu PSO was ran at f = 0.1, 0.3, 0.5, 0.7, and 0.9. The best result is shown. In four datasets f= 0.5 was the best in terms of accuracy and number of features except for the leukemia Golub dataset where f = 0.7 was better. Best results are shown in bold. value from an f-test. This forward-selection strategy is similar to that in PAM (Tibshirani et al., 2002) and the Prophet tool in GEPAS (Montaner et al., 2006).

We first compared our algorithm with the sbPSO. For the uuPSO runs, we used an overall controlling proxy parameter, size =10, then b = size, u = size, e = 1, n = 0.5*size, and m = 1.5*size. The results summarized in Table 2 are encouraging. Our algorithm increased remarkably the classification accuracy in all datasets, decreased the selected features from thousands to a handful, and decreased the computation time from days to about an hour. Best model accuracy improved from around 7.3% in Leukemia-Golub to 18.1% in BC. Moreover, remarkable differences are observed in model size and computation time where our algorithm gets better results by around two orders of magnitude. Overall, these results clearly show that our algorithm is able to obtain better predictive models from functional genomics data with thousands of features in a fraction of time.

and 11 active features respectively. This tendency toward lower values indicates that the optimal number of active features needed could be lower than 9. Considering these observations, there is a tendency for the number of active features closer to 6. A consequence of this result is that the shape of this distribution may suggest an estimation of the optimal value of the number of active features.

Table 6. Comparison of uuPSO algorithm using the nearest centroid (NC) and support vector machine (SVM) classifiers. The goodness (Accuracy) and number of features from the best model found among 100 runs is shown. Goodnesses and features mean and standard deviation (SD) were estimated along 1000 epochs and 100 runs. Time was estimated for 100 runs. A star (*) marks times estimated from partial results. generally smaller. These differences are consistent with the perception that SVM is a powerful classifier. However, we note a huge difference in processing time, which should correspond to the complex training procedure of SVM, to the java implementation used, or to our coupling implementation of this library. In the Ovarian dataset, uuPSO using SVM found models with 100% accuracy in early epochs explaining the small difference in processing time for this dataset.

Note: NLSE is the least squared error divided by the standard deviation of Y, and RSQ is the R-Square statistic from the regression. An NLSE of 0.0 is perfect while an RSQ of 1.0 is perfect. Table 1. Sample Test Problem Regressions Clearly the AEG symbolic regression runs are discovering and optimizing the embedded constants correctly; however, the standard GP symbolic regression runs are unable to optimize the constants and get confused. It is simply too difficult for standard GP to optimize these difficult embedded constants using only mutation and crossover. Furthermore, the standard GP runs produce estimators which are far from the correct form. The following are the top five estimators, produced by the standard GP symbolic regression, for test problem (14.1).

Note: Per annum compound returns for each decade. Theory and New Applications of Swarm Intelligence 13. Buying current earnings yield

The data supports the conclusion that even using this current revenue proxy model buying the top five, twenty five, and fifty stocks with the highest (current12MoEPS/currentPrice) produces above average securities investing profits, as least for the 1500 Valueline stocks, as shown in Table 3.

Predicting Corporate Forward 2 Month Earnings

The per annum returns using this symbolic regression revenue prediction model buying the top five , twenty five, and fifty stocks with the highest (regression12MoEPS/currentPrice, produces above average securities investing profits as shown in Table 7.

descriptionView Paper arrow_downwardDownload

Swarm Intelligence and Bio-Inspired Computation: Theory and Applications (Elsevier)

by Xin-She Yang

descriptionView Paper arrow_downwardDownload

Wisdom and foresight in Chinese thought: sensing the immediate future

by Dragos Simandan

2018, Journal of Futures Studies

This article provides an analysis of the problematic of foresight in traditional Chinese thought, articulating it with current developments in the epistemology of futures studies, planning theory, and strategic management. It is argued... more

descriptionView Paper arrow_downwardDownload

New Inspirations In Swarm Intelligence

by Rafael Stubs Parpinelli

2011

The growing complexity of real-world problems has motivated computer scientists to search for efficient problem-solving methods. Evolutionary Computation and Swarm Intelligence metaheuristics are outstanding examples that nature has been... more

descriptionView Paper arrow_downwardDownload

Swarm intelligence

by Pankesh Bamotra

2006, Handbook of Nature-Inspired and Innovative …

descriptionView Paper arrow_downwardDownload

Metaheuristic research: A comprehensive survey

by Kashif Hussain

2018, Artificial Intelligence Review

Because of successful implementations and high intensity, metaheuristic research has been extensively reported in literature, which covers algorithms, applications, comparisons, and analysis. Though, little has been evidenced on... more

these algorithms create a trajectory in the search space. Here, it is noteworthy that the solution may or may not belong to neighborhood of the current solution. For a population-based algorithm, a population of multiple solutions is generated initially. Then, in every iteration, a set of solutions are manipulated in order to find solutions toward better search areas. These algorithms either do recombinations of multiple solutions or modify each via the strategy adopted to enforce exploration and exploitation of the search area (Blum and Roli 2003). Now that the above discussion has already established preliminary knowledge about meta- je ES ns ne Se, mE ee, es ON oe i a ea ee en, or

Fig. 3. Publication venues with type of metaheuristic publications

The primary data collected in this study revealed around 140 metaheuristics (listed in ‘Appendix A”) applied in diversified range of fields broadly in the area of science and tech- 10logy, economics, and daily life. Fig. 4 infers that mostly metaheuristics have been applied and tested on numerical problems which include continuous and discrete, constrained and inconstrained, single and multi-objective optimization problems, etc. Data mining is another ield of interest mostly chosen by metaheuristic researchers, which includes optimization asks involved in classification, prediction, clustering, and system modeling, etc. Among top oractical applications, metaheursitics have been utilized to find optimum solutions for power eneration and distribution, and electronics board designing in the field of electrical and elec- ronics. Many industrial applications require scheduling jobs to be assigned on sequential yr parallel processes in order to optimized cost. Another promising area of metaheuristic ipplications is combinatorial optimization problems ranging from facility location problems O set-covering, to more difficult multi-agent task allocation in extreme teams, etc. Other ipplications among top ten areas include communications (networking, telecommunication, antennas and radar design, etc.), transportation (traveling salesman problem, routing, shortest oath, etc.), engineering (mechanical designs, aircraft and ship components design, etc.), civil sngineering (structural design, buildings and bridges, construction, etc.), and information and communications technology—ICT (cloud and grid computing, swarm robotics, security, software development, etc.). The applications of metaheuristics need to be explored in the ireas of mining, traffic control, manufacturing and production, etc.

Fig. 5 Number of publications of metaheuristics

Fig. 6 Metaphor disciplines adopted by researchers for designing metaheuristics

Fig. 7 Metaphors adopted by researchers for designing new metaheuristics

Table 1 Keywords and search results on the selected venues

Table 3 Metaheuristic applications on different domains

Table 4 continued Stochastic Diffusion Search (al Rifaie et al. 2011)

descriptionView Paper arrow_downwardDownload

Data mining with an ant colony optimization algorithm

by Ayushi Choudhary

2002, … , IEEE Transactions on

This paper proposes an algorithm for data mining called Ant-Miner (ant-colony-based data miner).

descriptionView Paper arrow_downwardDownload

Augmented Intelligence (keyword entry)

by Matteo Pasquinelli

Entry for Critical Keywords for the Digital Humanities (Leuphana University).

See also the diagram: https://www.academia.edu/15275569/Artificial_Intelligence_and_Its_Discontents

descriptionView Paper arrow_downwardDownload

A survey of network virtualization

by Kennedy Chinedu Okafor

2010, Computer Networks

Due to the existence of multiple stakeholders with conflicting goals and policies, alterations to the existing Internet are now limited to simple incremental updates; deployment of any new, radically different technology is next to... more

descriptionView Paper arrow_downwardDownload

A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms

by daniel molina

2011

The interest in nonparametric statistical analysis has grown recently in the field of computational intelligence. In many experimental studies, the lack of the required properties for a proper application of parametric procedures... more

Therefore, a pairwise comparison test, such as Wilcoxon’s test, should not be used to conduct various comparisons involving a set of algorithms, because the FWER is not controlled. In pairwise analysis, if we try to extract a conclusion involving more than one pairwise comparison, we will obtain an accumu: lated error coming from its combination. In statistical terms, we are losing the control on the Family-Wise Error Rate (FWER), definec as the probability of making one or more false discoveries amons all the hypotheses when performing multiple pairwise tests. The true statistical significance for combining pairwise comparisons i: given by

Average error obtained in the 25 benchmark functions.

Nonparametric statistical procedures considered in this tutorial. Table 2

ritical values for the two-tailed sign test at w = 0.05 anda = 0.1. An algorithm is significantly better than another if it performs better on at least the cases presented ach row. Table 5 Table 4

xample of Sign test for pairwise comparisons. SaDE shows a significant improvement over PSO, CHC, and SSGA, with a level of significance a = 0.05, and over SS-Arit, with level of significance a = 0.1. 3. Pairwise comparisons populations? It is anonparametric procedure employed in hypoth- esis testing situations, involving a design with two samples. This is analogous to the paired t-test in nonparametric statistical proce- dures; therefore, it is a pairwise test that aims to detect significant differences between two sample means, that is, the behavior of two algorithms.

Wilcoxon signed ranks test results. SADE shows an improvement over PSO, CHC, and SSGA, with a level of significance a = 0.01, over IPOP-CMA-ES and SS-Arit, wit a = 0.05, and over SS-BLX, with a = 0.1.

Friedman ranks (Example 4). Table 8 Friedman Aligned ranks (Example 4). Error rates achieved (Example 4). Table 7

Ranks achieved by the Friedman, Friedman Aligned, and Quade tests in the main case of study. DE-Exp achieves the best rank in the three procedures. The statistics computed and related p-values are also shown.

Friedman Aligned z-values and p-values (Example 6).

Quade z-values and p-values (Example 6).

Friedman z-values and p-values (Example 6).

Adjusted p-values for the Friedman Aligned test (DE-Exp is the control method).

Adjusted p-values for the Friedman test (DE-Exp is the control method).

Adjusted p-values for the Quade test (DE-Exp is the control method).

descriptionView Paper arrow_downwardDownload

A Survey of Swarm Algorithms Applied to Discrete Optimization Problems In: Swarm Intelligence and Bio-Inspired Computation 2013

by Rafael Stubs Parpinelli

2013

Jonas Krause, Jelson Cordeiro, Rafael Stubs Parpinelli, Heitor Silvério Lopes, A Survey of Swarm Algorithms Applied to Discrete Optimization Problems, In: Xin-She Yang, Zhihua Cui, Renbin Xiao, Amir Hossein Gandomi and Mehmet Karamanoglu,... more

A Survey of Swarm Algorithms Applied to Discrete Optimization Problems

2 eee MT ae Aon a Fee Figure 7.4 lists the encoding schemes (BC, IC, RTB, or RTI—see Section 7.3) 9% of the papers preferred to use the encodings directly as binary and 25% a nteger. In this approach, the solution vector is discrete and the algorithm cod ieeds to be modified accordingly to work with these values. For this purpose, sev ral authors created a discrete version of the continuous algorithm, e.g., the DPSC he CABC, and the DABC optimization. The other 55% of papers preferred to us he original continuous encoding then transforming them the real-valued vecto nto integer or binary, by using one of the methods presented in Section 7.3. Figure 7.5 is a more detailed view of the previous plot. It summarizes whic ncoding scheme was used in each algorithm and how many times these scheme

Figure 7.5 Encoding schemes related of swarm algorithms. A Survey of Swarm Algorithms Applied to Discrete Optimization Problems

Figure 7.6 Applications of the swarm algorithms.

descriptionView Paper arrow_downwardDownload

Particle Swarm Optimization: A Survey of Historical and Recent Developments with Hybridization Perspectives

by Saptarshi Sengupta

2018, Machine Learning and Knowledge Extraction

Particle Swarm Optimization (PSO) is a metaheuristic global optimization paradigm that has gained prominence in the last two decades due to its ease of application in unsupervised, complex multidimensional problems that cannot be solved... more

Table 9. 3D Plots of the Benchmark Functions. The results in Table 10 provide a high-level, intuitive understanding of benchmarking experiments using PSO and a few of its variants. In order to comment on the performance of the algorithms, statistical significance tests with an appropriate confidence level (generally alpha = 0.01 or 0.05) are commonly carried out.

Table 1. A collection of hybridized GA-PSO algorithms.

4.8.2. Hybridization of PSO Using Differential Evolution (DE) Table 1. Cont.

Table 2. A collection of hybridized DE-PSO algorithms. 4.8.3. Hybridization of PSO Using Simulated Annealing (SA)

4.8.4. Hybridization of PSO Using Ant Colony Optimization (ACO) Table 3. A collection of hybridized SA-PSO algorithms.

4.8.5. Hybridization of PSO Using Cuckoo Search (CS) Table 4. A collection of hybridized PSO-ACO algorithms.

Table 5. A collection of hybridized PSO-CS algorithms. 4.8.6. Hybridization of PSO Using Artificial Bee Colony (ABC)

Table 6. A collection of hybridized PSO-ABC algorithms. 4.8.7. Hybridization of PSO Using Other Social Metaheuristic Approaches The following section discusses some instances where the Particle Swarm Optimization algorithm has been hybridized with other commonly used social metaheuristic optimization algorithms for use in an array of engineering applications. Common techniques include Artificial Immune Systems [139-142], Bat Algorithm [143], Firefly Algorithm [144] and Glow Worm Swarm Optimization Algorithm [145].

Table 7. A collection of PSO algorithms hybridized with other approaches such as AIS, BA, FA and GSO. 4.9. Parallelized Implementations of PSO

Table 8. Benchmark Functions f1-/8. Table 9 shows the 3-dimensional representations of the benchmark functions (f 1-8).

Note: NR: Not Reported. Table 10. Performances of Some Variants of PSO on f1-f8.

descriptionView Paper arrow_downwardDownload

The next arms race? A military ethical reflection on the effects of artificial superintelligence on drone warfare and American counterterrorism

by Gabriel Boulianne Gobeil

The trend towards the automation and robotization of warfare, enabling the exercise of violence from a distance, has been long-present, dating back to such inventions as the bow and arrow that allowed an archer to kill from afar. Today’s... more

descriptionView Paper arrow_downwardDownload

The Eye of War: Military Perception from the Telescope to the Drone (University of Minnesota Press, 2018)

by Antoine Bousquet

2018

From ubiquitous surveillance to drone strikes that put “warheads onto foreheads,” we live in a world of globalized, individualized targeting. The perils are great. In The Eye of War, Antoine Bousquet provides both a sweeping historical... more

descriptionView Paper arrow_downwardDownload

A particle swarm optimization algorithm for the multiple-level warehouse layout design problem

by Umut Tuzkaya

2008, Computers & Industrial Engineering

‘ig. 1. A cross-section of the warehouse denoting the parameters.

When solution set is small, enlarging the solution set to cover some of the neighbor points can be a useful method to use. However, this wideness must shrink while the iteration number grows up, hence deviation from the constrictions can be diminished. JI© COMSUICUONS Cdll DU GQUMTNIsSTCa, Stretching the constrictions including the points on a specific approximation to the solution set is useful to »vercome this problem. But this elasticity should not be permanent; it should disappear to the maximum iter- ition so that we can reach to the real points ensuring the constrictions. This effect is shown in Fig. 3. On the sach iteration, original constriction value is stretched by a certain quantity. This elasticity changes according o the direction of the constriction too. Equation constrictions are positively and negatively stretched to reach in interval. If it is bigger than constriction, then the value is pulled to higher value, else the value is pulled to a ower value.

Fig. 5. Improving of the model variables in the iterations. Fig. 4. Model inputs and obtained results screen.

Fig. 6. Improving of the objective function value in the iterations.

Fig. 7. Scenarios applied to the main problem. There is one more main point related with the solution time of the PSO algorithm. All the scenarios are also solved by LINGO Release 9.0 which uses branch and bound algorithm (B and B) for pure integer nonlinear problems. LINGO is able to find only local optimum results with longer solution times in this problem. When the solution performance of PSO algorithm is compared with B and B, it is superior for most of the situations in terms of the solution times and number of iterations to reach to the best solution especially for scenarios that uses exponential height dimensions (Table 3). Furthermore, for all situations, PSO finds less than or equal cost objective values. As a result, even it is hard to compare an algorithm that gives optimal result and another algorithm that gives approximate result, it is proven that PSO is superior in terms of obtained objective values and solution times. a aa

ables are shown in Table 1. Also, Fig. 1 is given to visualize some of the dimensions given in Table 1. By using given details, a mathematical model providing the optimal number of storage spaces along a shelf and the optimum number of shelves is constituted. In other words, the three dimensions of the warehouse namely, length (wu), width (v) and height (4) are obtained by the model solution. The objective function of the model is constituted from the average travel distances in three dimensions and the unit material handling cost. Before giving the objective function and constraint formulations, some points should be clarified. The dock of the warehouse is located at the center of the horizontal wall. In the other word, the distance between the dock and the left vertical wall is u/2. Also, the probability of carrying an item to right or left side of the dock is equal. Therefore, the average travel distance in the horizontal axis is given in Eq. (1).

Comparison of the solution times of PSO algorithm versus branch and bound algorithm Table 3

The obtained results for 18 scenarios Table 2

descriptionView Paper arrow_downwardDownload

Social Algorithms

by Xin-She Yang

Glossary Social Algorithms • Algorithm: An algorithm is a step-by-step, computational procedure or a set of rules to be followed by a computer in calculations or computing an answer to a problem. • Ant colony optimization: Ant colony... more

Glossary Social Algorithms • Algorithm: An algorithm is a step-by-step, computational procedure or a set of rules to be followed by a computer in calculations or computing an answer to a problem. • Ant colony optimization: Ant colony optimization (ACO) is an algorithm for solving optimization problems such as routing problems using multiple agents. ACO mimics the local interactions of social ant colonies and the use of chemical messenger – pheromone to mark paths. No centralized control is used and the system evolves according to simple local interaction rules. • Bat algorithm: Bat algorithm (BA) is an algorithm for optimization, which uses frequency-tuning to mimic the basic behaviour of echolocation of microbats. BA also uses the variations of loudness and pulse emission rates and a solution vector to a problem corresponds to a position vector of a bat in the search space. Evolution of solutions follow two algorithmic equations for positions and frequencies. • Bees-inspired algorithms: Bees-inspired algorithms are a class of algorithms for optimization using the foraging characteristics of honeybees and their labour division to carry out search. Pheromone may also be used in some variants of bees-inspired algorithms. • Cuckoo Search: Cuckoo search (CS) is an optimization algorithm that mimics the brood parasitism of some cuckoo species. A solution to a problem is considered as an egg laid by a cuckoo. The evolution of solutions is carried out by Lévy flights and the similarity of solutions controlled by a switch probability. • Firefly algorithm: Firefly algorithm is an optimization inspired by the flashing patterns of tropical fireflies. The location of a firefly is equivalent to a solution vector to a problem, and the evolution of fireflies follows a nonlinear equation to simulate the attraction between fireflies of different brightness that is linked to the objective landscape of the problem. • Metaheuristic: Metaheuristic or metaheuristic algorithms are a class of optimization algorithms designed by drawing inspiration from nature. They are thus mostly nature-inspired algorithms, and examples of such metaheuristic algorithms are ant colony optimization, fire-fly algorithm, and particle swarm optimization. These algorithms are often swarm intelligence based algorithms. Nature-Inspired computation: Nature-inspired computation is an area of computer science, concerning the development and application of nature-inspired metaheuristic algorithms for optimization, data mining, machine learning and computational intelligence.

descriptionView Paper arrow_downwardDownload

Swarm Intelligence: Past, Present and Future

by Xin-She Yang

2017, Soft Computing

Many optimization problems in science and engineering are challenging to solve, and the current trend is to use swarm intelligence (SI) and SI-based algorithms to tackle such challenging problems. Some significant developments have been... more

descriptionView Paper arrow_downwardDownload

Swarm Intelligence and Bio-Inspired Computation

by Prof Mehmet Karamanoglu

2013, Swarm Intelligence and Bio-Inspired Computation

descriptionView Paper arrow_downwardDownload

Artificial intelligence and intelligence, by Giancarlo Elia Valori, Modern Diplomacy - Intelligence, February 22, 2018

by Dr. Matthew Crosston

descriptionView Paper arrow_downwardDownload

Bio-Inspired Computation and Applications in Image Processing

by Xin-She Yang and

A sample chapter of the Book on
"Bio-inspired Computation and Applications in Image Processing"
(Elsevier, 2016).

descriptionView Paper arrow_downwardDownload

Why the Firefly Algorithm Works

by Xin-She Yang

Firefly algorithm is a nature-inspired optimization algorithm and there have been significant developments since its appearance about ten years ago. This chapter summarizes the latest developments about the firefly algorithm and its... more

descriptionView Paper arrow_downwardDownload

An intelligent load forecasting expert system by integration of ant colony optimization, genetic algorithms and fuzzy logic

by Ahmad Ghanbari

2011, 2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)

Computational intelligence (CI) as an offshoot of artificial intelligence (AI), is becoming more and more widespread nowadays for solving different engineering problems. Especially by embracing Swarm Intelligence techniques such as ant... more

descriptionView Paper arrow_downwardDownload

Biogeography-based optimization

by abhishek rathi

2008, Evolutionary Computation, IEEE Transactions on

Fig. 1. Species model of a single habitat based on [3].

Fig. 2. Illustration of two candidate solutions to some problem. Sj is a rela- tively poor solution, while So is a relatively good solution.

Fig. 3. Schematic of an aircraft turbofan engine.

OPTIMIZATION RESULTS FOR THE SENSOR SELECTION PROBLEM. THE NUMBERS SHOWN ARE THE MINIMUM FUNCTION VALUES FOUND BY EACH ALGORITHM AVERAGED OVER 100 MONTE CARLO SIMULATIONS, AND THE BEST SOLUTIONS FOUND DURING THOSE 100 SIMULATIONS Fig. 4. Average sensor selection results of BBO without mutation, and BBO with probability-based mutation.

BENCHMARK FUNCTIONS. THE GRANULARITY OF EACH DOMAIN WAS 0.1 EXCEPT FOR THE QUARTIC FUNCTION, WHICH HAD A GRANULARITY OF 0.01 TABLE II MEAN NORMALIZED OPTIMIZATION RESULTS AND CPU TIMES ON BENCHMARK FUNCTIONS. THE NUMBERS SHOWN ARE THE MINIMUM FUNCTION VALUES FOUND BY THE ALGORITHMS, AVERAGED OVER 100 MONTE CARLO SIMULATIONS, AND NORMALIZED SO THAT THE SMALLEST NUMBER IN EACH Row Is 100. NOTE THAT THESE ARE NOT THE ABSOLUTE MINIMA FOUND BY EACH ALGORITHM, BUT THE AVERAGE MINIMA FOUND BY EACH ALGORITHM

single point crossover with a crossover probability of 1, and a mutation probability of 0.01. Benchmark results must always be taken with a grain of salt. First, we did not make any special effort to tune the optimization algorithms in this section. Different tuning parameter values in the optimization algorithms might result in significant changes in their performance. Second, real-world optimization problems may not have much of a relationship to benchmark functions. Third, benchmark tests might result in different conclusions if the grading criteria or problem setup change. In this section, we examined the mean and best results attained with a certain population size and after a certain number of generations. How- ever, we might arrive at different conclusions if (for example) we change the generation limit, or look at how many genera- tions it takes to reach a certain function value, or if we change the population size. In spite of these caveats, the benchmark re- sults shown here are promising for BBO, and indicate that this new paradigm might be able to find a niche among the plethora of population-based optimization algorithms.

BEST NORMALIZED OPTIMIZATION RESULTS ON BENCHMARK FUNCTIONS. THE NUMBERS SHOWN ARE THE BEST RESULTS FOUND AFTER 100 MONTE CARLO SIMULATIONS OF EACH ALGORITHM, AND NORMALIZED SO THAT THE SMALLEST NUMBER IN EACH Row Is 100. NOTE THAT THESE ARE THE ABSOLUTE BEST MINIMA FOUND BY EACH ALGORITHM

descriptionView Paper arrow_downwardDownload

New technology, same old strategy: Why artificial superintelligence represents the logical continuation of the US quest for war virtuousness

by Gabriel Boulianne Gobeil

2015, Journal of Military and Strategic Studies

Today’s military drones permit an extreme separation between rivals. Along with these weapons comes James Der Derian’s concept of virtuous war, which encapsulates a certain normative view of current and future wars. A rationale of the... more

descriptionView Paper arrow_downwardDownload

REVIEW ANALYSIS ON IMPORTANCE OF SWARM INTELLIGENCE AND ROBOTICS

by IJCSMC Journal and

2019, IJCSMC

Swarm robotic technology is the utilization of swarm intelligence principles to the control of robots groups. Active echolocation is a tangible methodology controlled by a variety of mammals and has utilized for the identifying,... more

descriptionView Paper arrow_downwardDownload

Solving Knight’s Tour Problem using Firefly Algorithm

by Amar Faiz Zainal Abidin

The knight’s tour problem is an ancient puzzle where the objective of the puzzle is to construct a series of legal moves made by a knight so that it visits every square of a chessboard exactly once. This paper proposes a model using... more

descriptionView Paper arrow_downwardDownload

A Social Spider Algorithm for Global Optimization

by Elhadi Chikh

The growing complexity of real-world problems has motivated computer scientists to search for efficient problemsolving methods. Metaheuristics based on evolutionary computation and swarm intelligence are outstanding examples of... more

* rand() is a random number uniformly generated in the range [0 1). * “SR” stands for “Shifted and Rotated”. o is a shifting vector and M is a transformation matrix. o and M can be optained from [22].

* This p-value is generated by the Kruskal-Wallis one-way analysis of variance.

RANK SUMMARY OF STATISTICAL ASSESSMENT RESULTS

* This p-value is generated by the the Wilcoxon signed rank test.

descriptionView Paper arrow_downwardDownload

Ant colony Optimization: A Solution of Load balancing in Cloud

by International Journal of Web & Semantic Technology (IJWesT)

As the cloud computing is a new style of computing over internet. It has many advantages along with some crucial issues to be resolved in order to improve reliability of cloud environment. These issues are related with the load... more

descriptionView Paper arrow_downwardDownload

Arquitectura Biodigital

by Marcelo Fraile Narváez

2019, Arquitectura Biodigital

La rápida e intensiva evolución que han experimentado las tecnologías biológicas y digitales a finales del siglo XX, han producido importantes transformaciones en nuestros hábitos cotidianos y laborales. En el campo específico de la... more

descriptionView Paper arrow_downwardDownload

A Review on Transformer Design Optimization and Performance Analysis Using Artificial Intelligence Techniques

by Mehta Hiren

descriptionView Paper arrow_downwardDownload

Swarm Intelligence as a Prosthetic Capacity

by James Haywood Rolling, Jr.

Swarm intelligence is the production of generative social space, the agency to “create and open spaces into which existing knowledge can extend, interrelate, coexist, and where new ideas and relationships can emerge prosthetically.” Swarm... more

descriptionView Paper arrow_downwardDownload

An improve d Opposition-Base d Sine Cosine Algorithm for global optimization

by Diego Oliva

Real life optimization problems require techniques that properly explore the search spaces to obtain the best solutions. In this sense, it is common that traditional optimization algorithms fail in local optimal values. The Sine Cosine... more

Fig. 1. The example of opposition-based optimization: (a) The contour plot of optimized function. (b) The optimized function.

Fig. 5. Convergence curves for fitness function from F13 to F18.

Fig. 7. Convergence curves for fitness function from F24 to F29.

Fig. 8. The parameters of welded beam design problem.

Fig. 9. The parameters of tension/compression spring problem. The optimization results of OBSCA and other algorithms for solving the welded beam design problem. 4.8.2. Tension/compression spring design The aim of this section is to analyze the performance of OBSCA to solve the tension/compression spring problem which aims to minimize the weight of tension/compression spring. In this prob- lem, there are three parameters namely, mean coil diameter (D), the number of active coils (N) and wire diameter (d). This problem is illustrated in Fig. 9 and it is defined as follows:

Fig. 10. The parameters of pressure vessel design problem. timal value of four variables (namely, the thickness of the head (T;,), thickness of the shell (Ts), the length of the cylindrical sec- tion without considering the head (L) and the inner radius (R)) that satisfied four constraints as (16):

*Fixed-dimension multimodal (Liang, Suganthan, & Deb, 2005), these functions are a combination of the unimodal and multimodal functions with different shift, ro- tation, and biasing. The composite functions are similar to other real search spaces and they are used to evaluate the performance of the algorithms to balance between the exploitation and explo- ration. functions by character “F’ and its number such as F1, F2, F3,... , F29. The functions from F1 to F7 are unimodal optimization problems which have one extreme value point within a given search area. These functions are used to investigate the convergence speed and optimization precision of the algorithms, while the functions from F8 to F23 are multimodal optimization functions which have more than one local one extreme value points within a given search area. They are used to evaluate the abilities to jump out of lo- cal optimum and seeking the global excellent result. The rest of benchmark functions (F24 to F29) are composite functions intro- duced by CEC 2005 special session (Suganthan et al., May 2005), The number N of agents in the population is fixed to 30 cor- responding to the dimension 30 and the maximum number of iterations is 500. The experiments are implemented over ”Win- dows 7 (64bit)” that runs on "CPU Core2 Duo with 4GB ram”; and "Matlab 2014b” software is used. For statistical analysis, all the

algorithms performed 30 independent runs over each benchmark problem.

Comparison between SCA and OBSCA over 11 fitness functions. Table 3 Table 2 Table 4 The results of test the Influence of Dimensionality.

The average of unimodal and multimodal functions function values for all algorithms. Table 6

Standard deviation of unimodal and multimodal functions for all algorithms. Table 7

The optimization results of OBSCA and other literatures for pressure vessel design problem. Table 14 HPSO (He & Wang, 2007b), CPSO (He & Wang, 2007a), ACO (Kaveh & Talatahari, 2010), CSCA (Huang et al., 2007), ES (Mezura- Montes & Coello, 2008), GA (Coello & Montes, 2002) (Deb, 1997), Lagrangian Multiplier (Kannan & Kramer, 1994), Branch-bound (Sandgren, 1990), and GSA (Mirjalili et al., 2016), as shown in Table 14. From Table 14 we can conclude that the results of OB- SCA is better than all other algorithms.

The optimization results of OBSCA and other literatures for tension/compression spring design problems. Table 13

descriptionView Paper arrow_downwardDownload

PhD thesis: The Cruel Drone -- Imagining Drone Warfare in Art, Culture and Politics

by Andreas Graae

2019, The Cruel Drone: Imagining Drone Warfare in Art, Culture, and Politics

The dissertation investigates how military UAV’s (unmanned aerial vehicles), or so-called drones, are represented within the aesthetic field as a “drone imaginary,” reflecting radical changes in the history of warfare. Using the imaginary... more

The dissertation investigates how military UAV’s (unmanned aerial vehicles), or so-called drones, are represented within the aesthetic field as a “drone imaginary,” reflecting radical changes in the history of warfare. Using the imaginary as a conceptual framework, the drone is analyzed as a cultural construct fueled with ideological and political imagination, including, above all, promises of liberation from the burdens and vulnerabilities of human lives and bodies in war. The main goal of the dissertation is to critically analyze how the drone imaginary builds on a fantasy of the perfect weapon which is, essentially, cruel. Drawing on Lauren Berlant’s thoughts and ideas, my claim is therefore that the social and cultural imagination of drone warfare follows a logic of cruel optimism. This means that the object for these desires, the drone, becomes an obstacle for its own flourishing by actively impeding the goal it promises to fulfill. In other words, my aim is to show how the popular attachment to drones is formed by fantasies and imaginations that are “cruel” in so far as they compromise themselves and obstruct their aims through a negative feedback loop, which constantly negates the promises these very same machines seem able to deliver on regarding a higher and safer mode of warfare.

Each of the chapters in the dissertation contains examples that demonstrate how these fantasies and promises in turn prove to be flawed or imperfect. Using the realm of aesthetics as prism, the analyses expose the darker side of this drone imagination focusing on its inherent cracks and frailties that altogether undermine the legitimacy as well as soundness of the fantasy of the drone as a new wonder-weapon. For instance, the analyses show how figurations of drone automation is uncannily non-human; how drone invincibility also entail trauma; how dreams of total vision become blurred by immensity; and how the myth of surgical precision ends up as carnage. Thus, each chapter specifically examines one of these drone figurations in order to show how they are con-figured into the larger drone imaginary.

Based on strategies of close-reading in combination with a cross-disciplinary conceptual approach, the dissertation offers new insights to the rapidly growing field of academic drone research. While this field has, however, so far mostly focused on the political, juridical, and ethical aspects of drone warfare and less on imaginary, literary, and aesthetic constructions and configurations vibrating beneath these debates, the dissertation contributes with an alternative cultural drone imaginary.

descriptionView Paper arrow_downwardDownload

WhereTo and Why – the Co-Evolution of Art, Science, and Technology

by Mark Frazier

2019, B-Future Forum

Author and historian Yuval Harari has foreseen a future where humans emerge as "self-made gods of planet Earth." Yet what may displace Homo Deus as the main mover in evolution? A prime candidate is a hybrid lifeform of greater scope. A... more

Author and historian Yuval Harari has foreseen a future where humans emerge as "self-made gods of planet Earth." Yet what may displace Homo Deus as the main mover in evolution? A prime candidate is a hybrid lifeform of greater scope. A new genus of superorganisms – Deus Narrans – will have an opportunity to engage actual and virtual beings across species lines in quests to co-evolve shared values, rather than advance a single genetic and memetic lineage. The art, technology and science endeavors arising from such new transspecies connectives may surpass in influence those of species-bound rivals. Exponential technologies will propel this transition. For eons, material scarcities prompted zero-sum rivalries among and between hominids and other species to reproduce at the expense of one another. As plenitude and longevity grow, new forms of non-zero sum interchange will arise among sentient beings. Evolution in a post-scarcity era will differ from earlier epochs by turning to the spread of lumenes -- replicable qualities of spirit (patterns of emotional response)-across species lines. New communication technologies and pattern languages can speed this shift. Technologies already are emerging for sentient beings to converse and share emotions among distantly-related animal and plant lifeforms. These tools will become central as evolution grows branchier. Genetic engineering and artificial intelligence soon will make Homo Sapiens the ancestor of myriad new cultures and species, many far surpassing our present capabilities. As a common ground for connecting sentient life forms, Deus Narrans can meet the need for spreading empathic resonances, understandings and collaboration among beings across species lines. The heart of such interactions may be a fractal system for co-creation in the realms of art, science, and technology. This paper maps how "social tetrahedrons" and “narrative fractals” can serve as interfaces through which sentient beings of all kinds can share experiences and create value at all scales in multiple realms. In the coming year, open source apps will begin testing such interfaces to bridge current cultural barriers in peer learning and online collaboration. If transcultural pilots succeed, they may set the stage for millions of humans – as well as individuals from new lifeforms to come – to explore, thrive, and co-evolve in relationships made possible by Deus Narrans.

Often, what we value often is conditional rather than static. In a Spirit-Mind-Body valuing triangle, the creator’s emotional, mental or physical wellbeing may change for better or worse. These changes can often affect what we most value. In a Personal-Business-Civic valuing triangle, there can be similar changes. Those who are personally dear to us may move from struggling to comfortable to flourishing conditions. Our Business ventures may fall from prosperous to a survival mode. Our Civic conditions may stay stable, unravel, or thrive.

Dozens — or hundreds — of valued people, places, projects and experiences can be added by an individual into such conditional valuing frames. Each person unfolds a unique pattern of valuing when populating a Social Tetrahedron — both in terms of what they choose to add to it, and where they place each valued item relative to the vertices and to the vertical axis. The valuing framework established by Social Tetrahedrons enables each creator to disclose as much (or as little) as they prefer to share about the values they deeply care about as a whole person.

VI. Mapping our higher selves The visibility settings of a Social Tetrahedrons can be set to either fully reveal, partially share, or keep hidden relationships of what they deem to be part of their extended /higher self. Visibility and access settings can be set by mutual agreement by creators of any associated Social Tetrahedrons. Such agreements also could define circumstances in which the creator of a related Social Tetrahedron could be delegated proxy rights to decide on the level of visibility. This feature would make it easier to manage access rights for third parties to view embedded Social Tetrahedrons across many levels of nesting.

Social Tetrahedrons also could be springboards for formation of mutual trust networks that become visible as distinct new Social Tetrahedrons. This could occur when individuals opt to display “trust tokens.” The tokens could show points where people and projects within one’s Social Tetrahedron also held delegated rights to curate one’s information flows in a given fielc of interest — and/or to act on one’s behalf. One-way or two-way delegations of trust in such cases would begin highlighting contours of an incipient larger holon - a trust network that could have its own identify grounded in shared Spirit-Mind-Body (and Personal-Business- Civic) frames of reference.

VII. Narrative Fractals: ensuring “alive and whole” initiatives

A possible further advantage Narrative Fractals may be depicted in a variety of feedback-sensitive ways. The following are possible visual conventions that might be used interspecies communications.*

Humpback whale tries to drive off an orca to save a seal (National Geographic) * An experiment might test peoples’ willingness to undertake altruistic actions benefiting unrelated others to ensure the reproductive success of a spirit /emotion replicator that they value in common. It might begin by introducing a randomly chosen group to recordings of actual cases of trans-species generosity. These might include dolphins saving a drowning human, a dog putting its life at risk to rescue a stranger's child, or a leopard sheltering a baby hyena. Then, participants in the experiment would be invited to make a choice.

Radiohead Composition (click here to play) As sensors and communications tools improve, humans are finding new ways to appreciate th beauty of life forms around us. Our arts are becoming more sensitive to the living currents around us, as reflected in a recent composition by Radiohead for BBC’s Blue Planet II documentary. III. Emergence of new voices and new sentient species

Through an imaginative experiment, researchers were able to get two extremely different animal species located far apart to interact with eact other and reach a shared decision with the help of robots. Robots enable bees and fish to talk to each other

The following diagram illustrates a simple drag-and-drop interface for populating a valuing triangle — showing each item that a sentient being values, and why.

descriptionView Paper arrow_downwardDownload

Creativity and the Arab Spring

by Alfonso Montuori

2013, East West Affairs

descriptionView Paper arrow_downwardDownload

Review on Elephant Herding Optimization Algorithm Performance in Solving Optimization Problems

by Saman M. Almufti

2018, international journal of engineering & technology

Elephant Herding optimization algorithm (EHO) is a metaheuristic swarm based search algorithm, which is used to solve various optimization problems. EHO can be used to solve as benchmark problems, Services Selection in QoS-Aware Web... more

descriptionView Paper arrow_downwardDownload

Ant Colony Optimization for Real-World Vehicle Routing Problems

by Roberto Montemanni

2007, Swarm Intelligence

Fig. 1 The forecast—-optimize—simulate loop: the role of optimization in the efficient management of a dis- tribution process 4.1 A VRPTW application for the secondary level in the supply chain

led to petal shaped tours. This preference was included in the reformulation of the problem, but at the same time we tried to loosen the constraint a bit. We attributed stores to distribu- tion regions, but at the same time we allowed stores near the border of the distribution region to also belong to the neighboring region. This allowed the generation of tours which were slightly worse than the unconstrained solution, but, nevertheless, better than the solutions found by the human planners. In Table | we present the results obtained by ANTROUTE compared with those of the human planners. ANTROUTE was run under two configurations: AR-RegTW, with regional planning and |-hour time windows; AR-Free, where the regional and the time windows constraints were relaxed. The problem was to distribute 52000 pal- lets to 6800 customers over a period of 20 days. Every day ANTROUTE was run on the available set of orders and it took about 5 minutes to find a solution. At the same time, the planners were at work and it took them at least 3 hours to find a solution. At the end of the testing period, the performances of the algorithm and of the planners have been compared using the same objective function. — 1 7 cr 1 out 11 64 fF 454 +, 7 oT . 1 1 a1

involves a limited number of orders, and the human planner performs well, the computer is not able to provide a significative improvement, but when the planner starts to fail coping with the problem complexity, and the performance decreases, the gain in using the algorithm sensibly increases. Table 2 Comparison of the computer-generated vs. man-made tours in the VRPPDTW application

The event manager receives new orders and keeps track of the already served orders and of the position and the residual capacity of each vehicle. This information is used to construct the sequence of static VRP-like instances. The working day is divided into time slices and for each of them a static VRP, which considers all the already received (but not yet executed) orders, is created. New orders received during a time slice are postponed until its end. At the end of each time slice, customers whose service time starts in the next time slice (according to the solution of the last static VRP) are assigned to the vehicles. They will not be taken into account in the following static VRPs. The ACS alonrithm amninved ic haced an the anne deceorihed in Gact 411 far the

descriptionView Paper arrow_downwardDownload

THE ARTIFICIAL INTELLIGENCE RACE: US, China, Russia, by Ecatarina Garcia, Modern Diplomacy, April 19, 2018

by Dr. Matthew Crosston

American Military University, School of Security and Global Studies, Doctoral Program in Strategic Intelligence.

descriptionView Paper arrow_downwardDownload

Swarm Intelligence: What Nature Teaches Us About Shaping Creative Leadership

by James Haywood Rolling, Jr.

A surprising look at the origins of creativity, and why future innovators are best forged through group collaboration and adaptive social networking. Companies and organizations everywhere cite creativity as the most desirable – and... more

descriptionView Paper arrow_downwardDownload

Ant Colony Algorithms for Data Classification

by Rafael Stubs Parpinelli

Ant Colony Optimization (ACO) is a relatively new computational intelligence paradigm inspired by the behaviour of natural ants . Ants often find the shortest path between a food source and the nest of the colony without using visual... more

descriptionView Paper arrow_downwardDownload

The Bees Algorithm - A Novel Tool for Complex Optimisation Problems

by The KOC

A new population-based search algorithm called the Bees Algorithm (BA) is presented. The algorithm mimics the food foraging behaviour of swarms of honey bees. In its basic version, the algorithm performs a kind of neighbourhood search... more

descriptionView Paper arrow_downwardDownload

Swarm Intelligence based Approach for Data Clustering

by Divya Gupta

Data Clustering is an important research topic in the field of data mining and a common technique for data analysis. This paper analyzes the shortcomings of standard Kmeans algorithm for data clustering and uses swarm intelligence methods... more

descriptionView Paper arrow_downwardDownload

Historical survey on metaheuristics algorithms

by Saman M. Almufti

2019, Science Publishing Corporation

Metaheuristic algorithms have been an interesting and widely used area for scientists, researchers and academicians because of their specific and significant characteristics and capabilities in solving optimization problems. Metaheuristic... more

Fig. 1: Metaheuristic Classifications. rithms are those in which a solution is randomly generated and improved until the optimum result is obtained, whereas population ba algorithms are those in which a set of solutions are randomly generated in a given search space and solution values are updated du iterations until the best solution is generated [2] , figure 1 shows the metaheuristic classifications. However, single solution based algorithms may trap into local optima which may prevent us to find global optimum as it reforms one solution, which is randomly generated for a given problem. On the other hand, population based algorithms have an inherent abi to escape local optima [2]. Due to this, nowadays, population based algorithms have gained the attention of multitudinous researchers. The categorization of population based algorithms is done on the basis of theory of evolutionary algorithms [201], physics laws ba algorithms, swarm intelligence of particles, and biological behavior of bio-inspired algorithms. Evolutionary algorithms are inspirec the evolutionary processes such as reproduction, mutation, recombination, and selection. These algorithms are based on the survival ness of candidate in a population (i.e., a set of solutions) for a given environment. The physics law based algorithms are inspired physical processes according to some physics rules such as gravitational force, electromagnetic force, inertia force, heating and coo! of materials. Swarm intelligence based algorithms are inspired by the collective intelligence of swarms[8]. Some of the most popular evolutionary algorithms are Genetic Algorithms (GA) [6] [203], Evolution Strategy (ES) [7], Differential E lution (DE) [8] [202], and Biogeography-Based Optimizer (BBO) [9]. A well-known algorithm of swarm intelligence technique is Particle Swarm Optimization (PSO) [10,11] [203], Elephant Herding O mization (EHO) [202]. PSO is inspired by the social behavior of fish schooling or bird flocking. Each particle can move around search space and update its current position with respect to the global best solution.

descriptionView Paper arrow_downwardDownload

A review of conventional and advanced MPPT algorithms for wind energy systems

by kalyan Chatterjee and

Wind power is the most reliable and developed renewable energy source over past decades. With the rapid penetration of the wind generators in the power system grid, it is very essential to utilize the maximum available power from the wind... more

descriptionView Paper arrow_downwardDownload

Parallel Approaches for the Artiﬁcial Bee Colony Algorithm

by Rafael Stubs Parpinelli

2011, Handbook of Swarm …

This work investigates the parallelization of the Artificial Bee Colony Algorithm. Besides a sequential version enhanced with local search, we compare three parallel models: master-slave, multi-hive with migrations, and hybrid... more