Self-organizing Algorithm Research Articles

Design of a Simple Self-Organizing and Multi-Hop Routing Algorithm Based on ZigBee Node

This paper briefly described the basic sensor network node architecture, point introduces the hardware design of the ZigBee Sensor nodes based on ATmega128L and CC2420, Power consumption of design node is low, smaller, higher integration, open to independent wireless communication module, multilayer, reducing the interference. And based on this hardware platform, Designed a self-organization Routing Protocol .Through networking experiments, verify the feasibility of the protocol. The protocol is very suitable for small-scale wireless sensor networks.

A neural network model to develop actions in urban complex systems represented by 2D meshes

The main idea of this work is to present a tool which may be useful to generate a mesh of points where urban actions may be taken after analysing and understanding complex urban situations. By the word complex we mean urban concentrations without precise limits and without a recognizable geometry pattern. In these situations, it is very hard for the architects to understand the system. Therefore, it is very difficult to define an action plan for this type of urban situations. What we propose is an adaptation of a neural network algorithm to work in the context of urban networks. Our objective is to develop a strategy to change this weakness of sparse urban development by activating public spaces with new meanings. A new 2D triangle mesh simplification model is introduced with the central property of preserving the shape of the original mesh. The mathematical model presented consists of a self-organizing algorithm whose objective is to generate the positions of the nodes of the simplified mesh; afterwards, a triangulation algorithm is carried out to reconstruct the triangles of the new simplified mesh. With this algorithm, it is possible to perform specific actions in an urban space, because the urban territory can be considered as a complex mesh with nodes and edges. A real example of an urban action is shown with the introduction of a wireless network in a residential area.

EFFECTS OF ADAPTIVE SOCIAL NETWORKS ON THE ROBUSTNESS OF EVOLUTIONARY ALGORITHMS

Biological networks are structurally adaptive and take on non-random topological properties that influence system robustness. Studies are only beginning to reveal how these structural features emerge, however the influence of component fitness and community cohesion (modularity) have attracted interest from the scientific community. In this study, we apply these concepts to an evolutionary algorithm and allow its population to self-organize using information that the population receives as it moves over a fitness landscape. More precisely, we employ fitness and clustering based topological operators for guiding network structural dynamics, which in turn are guided by population changes taking place over evolutionary time. To investigate the effect on evolution, experiments are conducted on six engineering design problems and six artificial test functions and compared against cellular genetic algorithms and panmictic evolutionary algorithm designs. Our results suggest that a self-organizing topology evolutionary algorithm can exhibit robust search behavior with strong performance observed over short and long time scales. More generally, the coevolution between a population and its topology may constitute a promising new paradigm for designing adaptive search heuristics.

Recovery properties of distributed cluster head election using reaction–diffusion

Chemical reaction–diffusion is a basic component of morphogenesis, and can be used to obtain interesting and unconventional self-organizing algorithms for swarms of autonomous agents, using natural or artificial chemistries. However, the performance of these algorithms in the face of disruptions has not been sufficiently studied. In this paper we evaluate the use of reaction–diffusion for the morphogenetic engineering of distributed coordination algorithms, in particular, cluster head election in a distributed computer system. We consider variants of reaction–diffusion systems around the activator–inhibitor model, able to produce spot patterns. We evaluate the robustness of these models against the deletion of activator peaks that signal the location of cluster heads, and the destruction of large patches of chemicals. Three models are selected for evaluation: the Gierer–Meinhardt Activator–Inhibitor model, the Activator–Substrate Depleted model, and the Gray–Scott model. Our results reveal a trade-off between these models. The Gierer–Meinhardt model is more stable, with rare failures, but is slower to recover from disruptions. The Gray–Scott model is able to recover more quickly, at the expense of more frequent failures. The Activator–Substrate model lies somewhere in the middle.

Method of evaluating diversity of carrot roots using a self-organizing map and image data

Carrot cultivars differ in nutritional value, and the quality of individual pieces may differ from the average, which can be troublesome for companies that process carrots. What is needed is a tool for quick confirmation of the existence and definition of the nature of the differences between the carrot roots. The aim of the experiment was to test whether the simple image parameters, such as colour, will determine the variation within populations of carrot and what kind of information about this differentiation may be provided by a self-organizing map. We indicated that the image data in combination with the self-organization algorithm can provide useful information about carrot roots. However analysis of each individual neural neuron could produce too many summaries to be useful. Therefore, the map was segmented into clusters using k-means method. Segmentation of the self-organizing map allowed to make a comprehensive evaluation of the roots. From the practical point of view such segmentation could help in sorting material, for example, taking into account suitability for processing. The proposed method is sensitive to changes in the processing features of the raw material and is able to locate it in the appropriate area of the topological map. This makes the processor can quickly check whether the raw material he received meets the standards established by a food processing plant. This information is important for the processing industry, in which final product parameters depend on the quality of raw material.

Self-organizing dual clustering considering spatial analysis and hybrid distance measures

Dual clustering performs object clustering in both spatial and non-spatial domains that cannot be dealt with well by traditional clustering methods. However, recent dual clustering research has often omitted spatial outliers, subjectively determined the weights of hybrid distance measures, and produced diverse clustering results. In this study, we first redefined the dual clustering problem and related concepts to highlight the clustering criteria. We then presented a self-organizing dual clustering algorithm (SDC) based on the self-organizing feature map and certain spatial analysis operations, including the Voronoi diagram and polygon aggregation and amalgamation. The algorithm employs a hybrid distance measure that combines geometric distance and non-spatial similarity, while the clustering spectrum analysis helps to determine the weight of non-spatial similarity in the measure. A case study was conducted on a spatial database of urban land price samples in Wuhan, China. SDC detected spatial outliers and clustered the points into spatially connective and attributively homogenous sub-groups. In particular, SDC revealed zonal areas that describe the actual distribution of land prices but were not demonstrated by other methods. SDC reduced the subjectivity in dual clustering.

An Object-Oriented Semantic Clustering Algorithm for High-Resolution Remote Sensing Images Using the Aspect Model

In this letter, we present a novel object-oriented semantic clustering algorithm for high-spatial-resolution remote sensing images using the probabilistic latent semantic analysis (PLSA) model coupled with neighborhood spatial information. First of all, an image collection is generated by partitioning a large satellite image into densely overlapped subimages. Then, the PLSA model is employed to model the image collection. Specifically, the image collection is partitioned into two subsets. One is used to learn topic models, where the number of topics is determined using a minimum description length criterion. The other is folded in using the learned topic models. Therefore, every pixel in each subimage has been allocated a topic label. At last, the cluster label of every pixel in the large satellite image is derived from the topic labels of multiple subimages which cover the pixel in the image collection. Experimental results over a QUICKBIRD image show that the clusters of the proposed algorithm are better than K-means and Iterative Self-Organizing Data Analysis Technique Algorithm in terms of object-oriented property.

A Self-Organization Algorithm for Robust Networking of Wireless Devices

This paper deals with distributed creation and maintaining of ad hoc networks including diverse wireless devices, namely sensors, PDA, cell phones, and video games consoles. A cluster-based self-organizing strategy is proposed for building a backbone among the mobile devices, detecting segmentation, and recovery. In this approach, each mobile device is controlled by a multi-role agent, which performs these tasks efficiently based only on local interactions; role management allows the backbone reconfiguration when the nodes leave or arrive to the network yielding a complex global emergent behavior. Energy saving is achieved by adapting the time interval and power of transmission after the network formation. Simulations showed that the distributed algorithms performance is close to that obtained by an optimizing global procedure.

Behavioural patterns as determinants of market movements: evidence from an emerging market

This article aims to empirically support the hypothesis that behavioural patterns are key determinants of market movements. We developed a model for predicting market psychology which is based on the application of a self-organizing network algorithm. The estimated model is applied to a mechanical trading system, which independently adopts investment decisions based on the current daily data. The model was tested on the data for daily trading on the Slovenian stock market as an example of an emerging capital market. The performance of the model supports the suggested hypothesis.

An application of a self-organizing model to the design of urban transport networks

A 2D triangle mesh simplification model is described in this paper, with the main objective of preserving the shape of the original mesh. The proposed model consists of a self-organizing algorithm whose objective is to generate the positions of the nodes of the simplified mesh; afterwards, a triangulation algorithm is performed to reconstruct the triangles of the new simplified mesh. The self-organizing algorithm is an unsupervised learning algorithm that provides a set of nodes representing the best approximation of the original mesh. An adaptation of the neural network algorithm is proposed with the primary objective to work in the context of urban transport networks. We verify the effectiveness of this model through the design and development of some urban network problems. Specifically, the algorithm is applied to two real problems, the first one is the design of a tramway network in a town, and the second one is the design of an information point network within a real bus transport network.

Brand-building in trade exhibition based on exhibitors’ perceived value

Trade exhibition industry has become an important part of Chinese economy. However, a lot of new trade exhibitions have been suffering from brand deficiencies which are severe obstacles in their development. How to discover the successful essentials in trade exhibitions and their synergetic mechanism, and propose a feasible brand-building strategy accordingly, which have become popular and difficult issues in exhibition industry. In this paper, we propose a system model which consists of three models named multivariate statistical analysis, bi-layer rough attributive reduction and uncertain self-organizing algorithm respectively, to mine the relationship between brand-building in trade exhibition and exhibitor perceived value with customer perceived value theory, brand-building theory and exhibition theory. Some critical successful essentials and their organic core influencing exhibitors’ perceived value are disclosed based on the survey information from the two representative trade exhibitions in China, and we point out that trade exhibition branding strategy is of two-dimensional characteristics, one emphasizing on ascending the internal competence and another emphasizing on adapting to external environment. The conclusion has been recognized by the managers and exhibitors of the two sampling exhibitions, which implies that the uncertain complex system method for analyzing the problem of brand-building in trade exhibition may be a new technical route to improve brand-building management system.

Tone recognition based on biomimetic pattern recognition theory

Pitch frequency trajectories can more truly reflect the tone characteristics of Mandarin.It is a better way to identify tone by identifying different pitch trajectories.According to the theory of biomimetic pattern recognition,an improved tone recognition algorithm was proposed.It used Iterative Self-Organizing Data Analysis Techniques Algorithm (ISODATA) to find centers of coverage areas,and multi-weight neural network to achieve coverage for each cluster center.The experimental results show that in the case of a small sample,the proposed algorithm can get a higher recognition rate than that of Hidden Markov model (HMM) and Support Vector Machine (SVM).

A self-organization mining based hybrid evolution learning for TSK-type fuzzy model design

In this paper, a self-organization mining based hybrid evolution (SOME) learning algorithm for designing a TSK-type fuzzy model (TFM) is proposed. In the proposed SOME, group-based symbiotic evolution (GSE) is adopted in which each group in the GSE represents a collection of only one fuzzy rule. The proposed SOME consists of structure learning and parameter learning. In structure learning, the proposed SOME uses a two-step self-organization algorithm to decide the suitable number of rules in a TFM. In parameter learning, the proposed SOME uses the data mining based selection strategy and data mining based crossover strategy to decide groups and parental groups by the data mining algorithm that called frequent pattern growth. Illustrative examples were conducted to verify the performance and applicability of the proposed SOME method.

ICIC in DL and UL with network distributed and self-organized resource assignment algorithms in LTE

Inter-cell Interference coordination (ICIC) has gained much interest in the 3rd Generation Partnership Project's (3GPP's) Long Term Evolution (LTE) standardization of a new air interface. Due to the new physical layer, interference can now be predicted and avoided on a frequency basis. Such schemes are based on cell wise usage restrictions or resource preferences. After explaining the general degrees of freedom, we present an “inverted” reuse scheme for downlink and uplink and explain its advantages. This is supported by 3GPP-compliant system simulations. The question of assignment of restrictions or preferences naturally leads to a need for self-organization. For that, the concept of semi-static ICIC based on a request-grant mechanism applicable to load balancing is explained. For the static ICIC case with frequency planning, a novel and fully distributed algorithm provides optimized assignment of resource restrictions to the cells in a self-organizing way. It is capable of resolving sub-optimal aspects and comprises methods to detect and prevent possible system instabilities. The algorithms presented lead to an integrated ICIC-self-organizing network (SON) concept that can be realized in a multi-cell network solution.

Self-Organized Data Ecologies for Pervasive Situation-Aware Services: The Knowledge Networks Approach

Pervasive computing services exploit information about the physical world both to adapt their own behavior in a context-aware way and to deliver to users enhanced means of interaction with their surrounding environment. The technology to acquire digital information about the physical world is becoming more available, making services at risk of being overwhelmed by such growing amounts of data. This calls for novel approaches to represent and automatically organize, aggregate, and prune such data before delivering them to services. In particular, individual data items should form a sort of self-organized ecology in which, by linking and combining with each other into sorts of “knowledge networks” (KNs), they are able to provide compact and easy-to-be-managed higher level knowledge about situations occurring in the environment. In this context, the contribution of this paper is twofold. First, with the help of a simple case study, we motivate the need to evolve from models of “context awareness” toward models of “situation awareness” via proper self-organized “KN” tools, and we introduce a general reference architecture for KNs. Second, we describe the design and implementation of a KN toolkit that we have developed, and we exemplify and evaluate algorithms for knowledge self-organization integrated within it. Open issues and future research directions are also discussed.

Intrusion Detection Based on Self-Organizing Map and Artificial Immunisation Algorithm

The rate of false positives which caused by the variability of environment and user behavior limits the applications of intrusion detecting system in real world. Intrusion detection is an important technique in the defense-in-depth network security framework and a hot topic in computer security in recent years. To solve the intrusion detection question, we introduce the self-organizing map and artificial immunisation algorithm into intrusion detection. In this paper, we give an method of rule extraction based on self-organizing map and artificial immunisation algorithm and used in intrusion detection. After illustrating our model with a representative dataset and applying it to the real-world datasets MIT lpr system calls. The experimental result shown that We propose an idea of learning different representations for system call arguments. Results indicate that this information can be effectively used for detecting more attacks with reasonable space and time overhead. So our experiment is feasible and effective that using in intrusion detection.

Genetic Structure of a Rural Region in Spain: Distribution of Surnames and Gene Flow

The biodemography of isolated populations with a subsistence economy is of special interest because the conditions to which the populations have been subjected are similar to those present over a large part of the history of our species, and hence the conclusions drawn can be extrapolated to other similar populations. In the present work, we used two recently employed techniques (self-organizing maps and Monmonier's algorithm) to study the genetic structure of a small rural region: Fuentes Carrionas (province of Palencia, Spain). The study was based on information contained in marriage registers and family reconstructions for the period 1880-1979. We calculated the coefficients of relationships (Hedrick) among the parishes (by isonymy and parent-offspring matrix) and studied their relationship with geographic distances (Mantel). Then, using Monmonier's algorithm, we examined the genetic barriers. Finally, by applying self-organizing maps, we studied the distribution of surnames. The correlation between genetic distance matrices estimated through surnames and gene flow was high (p < 0.01), and geographic distance was found to be significantly related to both surnames and gene flow (p < 0.01); geographic distance therefore seems to be the main factor of isolation. However, the genetic barriers revealed a region divided in two, and the surname distribution displayed an identical division: 29.56% of the surnames appeared almost exclusively in the northeastern half and 21.91% appeared only in the southwest. Both techniques afforded coherent and complementary results. Their combined use allows a detailed study to be made. Although geographic distance was the strongest determining factor, we detected others factors (orographic and socioeconomic) that seem to have left their mark on the genetic structure of Fuentes Carrionas.

A model to simplify 2D triangle meshes with irregular shapes

We present a 2D triangle mesh simplification model which is able to produce high quality approximations of any original planar mesh, regardless of the shape of the original mesh. This method consists of two phases: a self-organizing algorithm and a triangulation algorithm. The self-organizing algorithm is an unsupervised incremental clustering algorithm which provides us a set of nodes representing the best approximation of the original mesh. The triangulation algorithm reconstructs the simplified mesh from the planar points obtained by the self-organizing training process. Some examples are detailed with the purpose of demonstrating the ability of the model to perform the task of simplifying an original mesh with irregular shape.

Self-organized clustering algorithm based on regional relevance in wireless sensor network

In view of limited resources and amounts of data in Wireless Sensor Network(WSN),clustering compressions are always employed to reduce transmission packets.Based on the regional relevance,a self-organized clustering algorithm was proposed for the wavelet compression in sensor network.The algorithm used the correlation of actual regional data for clustering.Actually,during the wavelet data compression procedure,the data correlation was detected in the cluster head,so that to insure better correlation and adjust the clusters structure.Meanwhile,data dependence among the nodes was analyzed in Sink,to form large-scale clusters with better relevance,so that to improve the efficiency of wavelet compression in a long period.Theoretical and experimental results show that the proposed algorithm can eliminate the data redundancy by using temporal and spatial correlation as much as possible,improve the efficiency of wavelet data compression,and reduce network energy consumption.

Constrained multiple traveling salesman problem based on self-organizing optimization algorithm

The Multiple Traveling Salesman Problem(MTSP) is an extension of the traveling salesman problem(TSP).MTSP is a classical combinatorial optimization problem with more complexity and applicability.The MTSP with the up-limit of the cities to be visited for each salesman was studied and the self-organizing algorithm(SOA) was introduced to solve the problem.The MTSP was transformed into a TSP by introducing virtual cities and the local fitness of virtual city was defined to deal with the relevant constraints.The computational results with a number of benchmark problems show that SOA can be effectively applied in solving the proposed MTSP with superior performance.