Search

Purpose: To profile the participants using a system of self-organizing maps (SOM) based on their motor and cognitive performance during a dual-task version of the Canadian Agility and Movement Skill Assessment (Cognitive CAMSA). Methods: A total of 169 secondary school students (39.3% girls) volunteered to participate. The original CAMSA, cognitive CAMSA, the Corsi and Digit Span tests were used to assess (a) motor competence, (b) motor competence with cognitive load, and (c) cognitive performance, respectively. SOMs and the k-means clustering algorithm were used to establish the adolescents’ dual-task performance profiles. Results: Including decision making based on verbal and visual cues in the original CAMSA significantly increased the participants’ total scores but also the time required to complete the test, while the skill score remained unchanged. However, not all the participants showed changes in their performance in the same direction during the cognitive CAMSA. Person-centered analyses by SOMs and k-means clustering identified six performance profiles with variations in the cognitive, motor skill, and time scores (H5 = 146.15, H5 = 102.68, and H5 = 108.07, respectively; all p < 0.01). Conclusion: The cognitive CAMSA was shown to be a feasible field-motor test for assessing motor competence with a cognitive load in an ecological setting. Some of the profiles identified in the SOM approach represented adolescents with similar motor and cognitive performance in dual-task or single-task contexts, although other participants obtained high motor competence in single and dual-tasking while their cognitive performance declined or rose more in dual-task than in single task situations. The cognitive CAMSA emerges as a tool of great potential, applicable in educational and sports environments, to know subjects’ characteristics and try to individualize the interventions accordingly with their dual-task profile. [ABSTRACT FROM AUTHOR]

Modern industry has become very complex and requires an equally complex engineering technology system, which includes resource utilization, energy conversion, product research and development, technological innovation, environmental protection and industrial ecology, and other aspects of the system. Continued development of large-scale, streamlined, and continuous processes is critical; however, there are also problems such as data redundancy, overcapacity, redundant construction, and waste of resources. Based on the system synergy theory, this paper introduces the system analysis method from the perspective of flow structure, with the purpose of solving the management defects of complex industrial production systems. First, we analyze the complex industrial production system as a collaborative structure of three subsystems: material flow, energy flow, and information flow. The following concepts are clarified: "material flow is the main body, energy flow is attached to and drives material flow, material flow and energy flow generate information flow, and information flow reversely drives material flow and energy flow". Secondly, the collaborative evolution process of the complex industrial production system is divided into three periods, which are the generation period, the stalemate period, and the maturity period, and a synergy degree evaluation model is established, which considers the Theil index and subsystem gray correlation method, and extends the dynamic differential equation model of three-stage collaborative evolution. Subsequently, we used MATLAB numerical simulation to demonstrate that the collaborative evolution of production systems is related to four aspects. They are the self-organizing ability of the system, the dominant role of order parameters, the competition and cooperation between order parameters, and whether mutations can become order parameters. At the same time, it was also found that it is basically independent of other factors, such as attenuation inertia. Then, the self-organizing map network (SOM) algorithm was used for the rapid identification of mutation data. Finally, we use the empirical research of SG enterprises to show that their production level and management system are advanced, but they were in a non-cooperative state from 2014 to 2021. In 2022, they had the basic conditions and trends to enter the synergistic generation period, and a synergistic management model is required. At the end of the article, we give a collaborative management method for complex industrial enterprises with a good management foundation. These include the management mechanism based on flow structure collaboration and the management path based on collaborative evolution. Of course, the management countermeasures given in this study are also applicable to other complex process-based industrial enterprises. [ABSTRACT FROM AUTHOR]

This article proposes a kernel‐based regularization least squares algorithm for nonlinear time‐delayed systems with unknown structure. Since the structure and the time‐delay of the model are unknown, a model pool constituted of several Volterra series is constructed with the aim of approximating the nonlinear model which has different time‐delays. Then, a self‐organizing maps method and a kernel‐based regularization method are interactively used to update the time‐delay and parameters. Compared with the traditional algorithms, the proposed algorithm has no limitation on the nonlinear model, and can describe the dynamics of the nonlinear model with a simple structure. Finally, simulation examples are given to show the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Self Organizing Maps (SOM) are unsupervised neural networks suited for visualisation purposes and clustering analysis. This study uses SOM to solve a software engineering problem: detecting the most important (key) classes from software projects. Key classes are meant to link the most valuable concepts of a software system and in general these are found in the solution documentation. UML models created in the design phase become deprecated in time and tend to be a source of confusion for large legacy software. Therefore, developers try to reconstruct class diagrams from the source code using reverse engineering. However, the resulting diagram is often very cluttered and difficult to understand. There is an interest for automatic tools for building concise class diagrams, but the machine learning possibilities are not fully explored at the moment. This paper proposes two possible algorithms to transform SOM in a classification algorithm to solve this task, which involves separating the important classes - that should be on the diagrams - from the others, less important ones. Moreover, SOM is a reliable visualization tool which able to provide an insight about the structure of the analysed projects. [ABSTRACT FROM AUTHOR]

Organising and optimising production in small and medium enterprises with batch production and many different products can be very difficult due to high complexity of possible solutions. The paper presents a method of fine layout planning that rearranges production resources and minimises work and material flow transfer between production cells. The method is based on self-organising map clustering which organises the production cells into groups sharing similar product properties. The proposed method improves the internal layout of each cell with respect to a material flow diagram and a from-to matrix, and fine workspace positioning also considers various restrictions on placement, specifications and types of transportation. The method is particularly suitable for improving the existing layouts. The method was applied in the Slovenian company KGL d.o.o. and promising results were achieved. A reduction by more than 40% in the total transport length with respect to the current production layout was observed. [ABSTRACT FROM PUBLISHER]

Forest inventory based on airborne laser scanning produces data for small grid cells. Various segmentation methods are used to cluster the grid cells into spatially continuous larger areas that correspond to forest stands. This study examined the performance of self-organizing map (SOM) in the delineation of forest stands. The SOM is also called Kohonen map or Kohonen network, according to the developer of the method. The data consisted of stand attribute grids in 16-m resolution. Spatiality was integrated in the SOM by using the geographical coordinates as criteria in the clustering. The clusters created by the SOM were spatially distinct and formed continuous areas corresponding to traditional stands when geographical coordinates were given more weight in the clustering compared to other stand attributes such as fertility class and stand basal area. The delineation improved when the attributes of the created stands were used as the starting point of repeated SOM rounds, and removing small stands at the beginning of each round. When small within-stand variation in stand attributes was targeted, the SOM often produced irregular stands consisting of disconnected parts. These delineations could be fine-tuned by applying mode filtering to the grid of stand numbers generated by the SOM algorithm. [ABSTRACT FROM AUTHOR]

In this paper, a novel cognitive architecture for action recognition is developed by applying layers of growing grid neural networks. Using these layers makes the system capable of automatically arranging its representational structure. In addition to the expansion of the neural map during the growth phase, the system is provided with a prior knowledge of the input space, which increases the processing speed of the learning phase. Apart from two layers of growing grid networks the architecture is composed of a preprocessing layer, an ordered vector representation layer and a one-layer supervised neural network. These layers are designed to solve the action recognition problem. The first-layer growing grid receives the input data of human actions and the neural map generates an action pattern vector representing each action sequence by connecting the elicited activation of the trained map. The pattern vectors are then sent to the ordered vector representation layer to build the time-invariant input vectors of key activations for the second-layer growing grid. The second-layer growing grid categorizes the input vectors to the corresponding action clusters/sub-clusters and finally the one-layer supervised neural network labels the shaped clusters with action labels. Three experiments using different datasets of actions show that the system is capable of learning to categorize the actions quickly and efficiently. The performance of the growing grid architecture is compared with the results from a system based on Self-Organizing Maps, showing that the growing grid architecture performs significantly superior on the action recognition tasks. [ABSTRACT FROM AUTHOR]

The autofocus level of the microscope is one of the factors that affect the user's work efficiency. In this paper, in order to improve the efficiency of the search algorithm while ensuring the search accuracy, a focus search algorithm with the function of predicting the best focus position based on the SOM neural network is proposed. The search algorithm makes full use of the automatic clustering function of SOM neural network. First complete the training of the SOM neural network through a large number of samples. The trained SOM neural network can directly predict the best focus position of the lens based on the input sample data. The results show that the auto-focusing algorithm proposed in this paper has high stability, and the probability of successful auto-focusing is not less than 94%. In terms of clarity threshold selection, it should be based on the number of cells. As for the clarity curve, the curve of the energy spectrum method has obvious peaks and high sensitivity. In terms of the real-time nature of autofocus, the motor is a key factor restricting the focusing speed. [ABSTRACT FROM AUTHOR]

The Kohonen Self-Organizing Map (SOM) is an unsupervised learning technique for summarizing high-dimensional data so that similar inputs are, in general, mapped close to one another. When applied to textual data, SOM has been shown to be able to group together related concepts in a data collection and to present major topics within the collection with larger regions. This article presents research in which the authors sought to validate these properties of SOM, called the Proximity and Size Hypotheses, through a user evaluation study. Building upon their previous research in automatic concept generation and classification, they demonstrated that the Kohonen SOM was able to perform concept clustering effectively, based on its concept precision and recall 7 scores as judged by human experts. They also demonstrated a positive relationship between the size of an SOM region and the number of documents contained in the region. They believe this research has established the Kohonen SOM algorithm as an intuitively appealing and promising neural-network-based textual classification technique for addressing part of the longstanding "information overload" problem. [ABSTRACT FROM AUTHOR]

Extractive text summarization yields the sensitive parts of the document by neglecting the irrelevant and redundant information. In this paper, we propose a new strategy for extractive single-document summarization in Malayalam. Initially, entity recognition is done, followed by relevance analysis is made based on some context-aware features. The scored sentences are then clustered using self-organizing maps (SOM) and from these clusters, relevant sentences are extracted out based on the proposed algorithm. Both theoretical and practical evaluations are done to analyze the implemented system. In theoretical evaluation, gradient calculations of relevance equations are used to know that which of these sentence scoring features are contributing more. The relevance equation is optimized with the help of Lagrange's multiplier. The complexity analysis of the proposed algorithms is also performed. In practical evaluation, the system compared with online and offline summarizers upon metrics like precision, recall, and F-measure. The system is tested through a non-clustering approach also in order to analyze the impact of clustering used in our work. Some existing strategies like question game evaluation, sentence rank evaluation, and keyword association are also done to evaluate the different parameters like the relevance of sentences, important entity words, etc. [ABSTRACT FROM AUTHOR]

E-learning personalization aims to deliver learning activities and materials that suits to learners' needs. Therefore, the system must have the ability to analyze the profile and characteristics of each individual learner. Characteristics of learners, among others, can be identified from their behavior in using e-learning. Their most frequent learning resource accessed, their participation on discussions, and their assessment result are some of the variables from the activity logs that can describe their learning patterns. On the other side, learners' behavior may change over time. This research aims to capture and analyze the dynamic learning pattern throughout the semester. The learning analytics are conducted using temporal clustering approach to identify the learning style, motivation, and knowledge abilities. This research performs two-level clustering analysis to acquire learning patterns from activity logs from Moodle Learning Management System using Self-Organizing Map (SOM) and k-Means. SOM enables visualization high dimensional data by projection to lower dimensions. The proto-clusters of SOM are then clustered using k-Means. The temporal clustering results show that the learning patterns of learners are changing over time. [ABSTRACT FROM AUTHOR]

Maintenance is essential to ensure safe operation of equipment in normal conditions. Therefore, managers must identify the relative priorities and equipment maintenance requirements. Moreover, based on the results of equipment vulnerability assessments, maintenance programs can be developed and managed properly. There are different methods and techniques in the process of risk assessment and management and vulnerability of equipment. Seventy-six samples with different properties have been used in this study. Networks used in this study are self-organizing networks with constant weight, which include Kohonen networks. For this purpose, operation impact, operation flexibility, maintenance cost, impact of safety and environment and frequency parameters had been considered as input; and using this model, the risk level is calculated. Utilizing genetic algorithms, the structures of all self-organizing systems are optimized. In order to evaluate the accuracy of the model, we compare it with the fuzzy model, and the results indicate that self-organizing systems optimized with the genetic algorithm have higher ability, flexibility and accuracy than the fuzzy model in predicting risk. [ABSTRACT FROM AUTHOR]

Featured Application: The methodology presented in this paper is directly intended for application in the area of turbojet engines. This paper presents the design of an automated system which can create diagnostic information using data from an infrared thermal camera, utilizing methods of computational intelligence and expert systems, which can be considered as a novel approach. The developed system segments infrared images use a self-organizing feature map and an expert system to automatically extract diagnostic information about the technical state of a turbojet engine. The diagnostic system was developed using a small iSTC-21v turbojet engine with a thrust of 500 N in laboratory conditions and can be simply modified for application to other engine types. The system is not limited to engines and can be considered for application in other technical systems which produce heat, such as generators, transmissions, and electronic circuit boards. There are only a few applications of infrared thermal imaging in aviation. In the area of turbojet engines, infrared imaging has been used to detect temperature field anomalies in order to identify structural defects in the materials of engine casings or other engine parts. In aviation applications, the evaluation of infrared images is usually performed manually by an expert. This paper deals with the design of an automatic intelligent system which evaluates the technical state and diagnoses a turbojet engine during its operation based on infrared thermal (IRT) images. A hybrid system interconnecting a self-organizing feature map and an expert system is designed for this purpose. A Kohonen neural network (the self-organizing feature map) is successfully applied to segment IRT images of a turbojet engine with high precision, and the expert system is then used to create diagnostic information from the segmented images. This paper represents a proof of concept of this hybrid system using data from a small iSTC-21v turbojet engine operating in laboratory conditions. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to sensor-based feature evaluation and selection using a self-organizing map and spatial statistics as a combined technique applied to tool condition monitoring of the turning process. This approach takes advantage of the unique features of unsupervised neural networks combined with spatial statistics to perform analyses into the contributions of the different sensor-based features, carrying large quantities of noise, to achieve a classification of tool wear and a quantitative measure of each feature's suitability. This method does not assume a prior direct correlation between features avoiding misconstructions inherent to common approaches that assume that only obviously correlated features should be considered for condition monitoring. Instead, and taking advantage of neural networks ability to perform non-linear modeling, it has allowed a prior modeling of the process and then analyzed each feature's contribution toward classification. It was found that some of the commonly used features have proven to have a significant contribution to the classification of cutting tool wear, whereas others adversely affect classification performance. Further, it is demonstrated that the proposed combined technique can be used extensively to quantitatively evaluate the contribution of different features toward system monitoring in the presence of noisy data. [ABSTRACT FROM AUTHOR]

Both all-connection model and part connection model is simulated, which adopt self-organizing map neural network to generate check bits. Consequently, N source bits and K check bits are composed a complete codeword. In the decoding port, multi-layer perceptron network (MLPN) is utilized to implement decoding function. The specific steps are as follows: (1) Constructing the MLPN according to the size of codeword sets and source bits; (2) Training the MLPN with codeword sets generated by neural network decoder until qualified; (3) Accepting and decoding codeword sets via trained MLPN. Actual tests show that: (1) There exist no evident performance differences between all-connection model and part-connection model; (2) The connection of weight sets is similar to Tanner graph in part-connection model, which reduce the computational complex greatly and remain good performance at the same time. In sum, the method of encoding and decoding has certain market prospect in confidential communication field. [ABSTRACT FROM AUTHOR]

Kohonen’s Self Organizing feature Map (SOM) provides an effective way to project high dimensional input features onto a low dimensional display space while preserving the topological relationships among the input features. Recent advances in algorithms that take advantages of modern computing hardware introduced the concept of high resolution SOMs (HRSOMs). This paper investigates the capabilities and applicability of the HRSOM as a visualization tool for cluster analysis and its suitabilities to serve as a pre-processor in ensemble learning models. The evaluation is conducted on a number of established benchmarks and real-world learning problems, namely, the policeman benchmark, two web spam detection problems, a network intrusion detection problem, and a malware detection problem. It is found that the visualization resulted from an HRSOM provides new insights concerning these learning problems. It is furthermore shown empirically that broad benefits from the use of HRSOMs in both clustering and classification problems can be expected. [ABSTRACT FROM AUTHOR]

In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoencoders. We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map. In so doing the parameters are adjusted by the proposed unsupervised learning algorithm. The model therefore maintains the clustering properties of its predecessor, whereas by extending and enhancing its visualization capacity enables an inclusion and an analysis of the intermediate representation space. A comprehensive series of experiments comprising optical recognition of text and images, and cancer type clustering and categorization is used to demonstrate DASOM’s efficiency, performance and projection capabilities. [ABSTRACT FROM AUTHOR]

Colour distortion, which is caused by the unavoidable mismatch between a map’s gamut and a device’s gamut, negatively affects the semiotic quality of maps. Cartographic communication often suffers from undesirable colour inconsistency. This method models cartographic colour reproduction as a constrained transform problem, namely, adapting a map’s gamut to fit a device’s gamut while preserving the semiotic quality. First, the characteristics of the map’s gamut are investigated by considering cartographic principles, and the fundamental concerns of preserving semiotic quality are proposed. Then, the self-organizing map method is introduced to iteratively optimize the cartographic colour reproduction. We implement this method and evaluate it based on a series of thematic maps. The results indicate that the proposed algorithm offers better results than two alternatives in terms of facilitating cartographic colour reproduction. [ABSTRACT FROM AUTHOR]

The spectrum of a galaxy contains information about its physical properties. Classifying spectra using templates helps to elucidate the nature of a galaxy’s energy sources. In this paper, we investigate the use of self-organizing maps in classifying galaxy spectra against templates. We trained semi-supervised self-organizing map networks using a set of templates covering the wavelength range from far ultraviolet to near-infrared. The trained networks were used to classify the spectra of a sample of 142 galaxies with 0.5 < $$z$$ < 1 and the results compared to classifications performed using K -means clustering, a supervised neural network, and chi-squared minimization. Spectra corresponding to quiescent galaxies were more likely to be classified similarly by all methods while starburst spectra showed more variability. Compared to classification using chi-squared minimization or the supervised neural network, the galaxies classed together by the self-organizing map had more similar spectra. The class ordering provided by the 1D self-organizing maps corresponds to an ordering in physical properties, a potentially important feature for the exploration of large data sets. [ABSTRACT FROM AUTHOR]

Data collected in psychological studies are mainly characterized by containing a large number of variables (multidimensional data sets). Analyzing multidimensional data can be a difficult task, especially if only classical approaches are used (hypothesis tests, analyses of variance, linear models, etc.). Regarding multidimensional models, visual techniques play an important role because they can show the relationships among variables in a data set. Parallel coordinates and Chernoff faces are good examples of this. This article presents self-organizing maps (SOM), a multivariate visual data mining technique used to provide global visualizations of all the data. This technique is presented as a tutorial with the aim of showing its capabilities, how it works, and how to interpret its results. Specifically, SOM analysis has been applied to analyze the data collected in a study on the efficacy of a cognitive and behavioral treatment (CBT) for childhood obesity. The objective of the CBT was to modify the eating habits and level of physical activity in a sample of children with overweight and obesity. Children were randomized into two treatment conditions: CBT traditional procedure (face-to-face sessions) and CBT supported by a web platform. In order to analyze their progress in the acquisition of healthier habits, self-register techniques were used to record dietary behavior and physical activity. In the traditional CBT condition, children completed the self-register using a paper-and-pencil procedure, while in the web platform condition, participants completed the self-register using an electronic personal digital assistant. Results showed the potential of SOM for analyzing the large amount of data necessary to study the acquisition of new habits in a childhood obesity treatment. Currently, the high prevalence of childhood obesity points to the need to develop strategies to manage a large number of data in order to design procedures adapted to personal characteristics and increase treatment efficacy. [ABSTRACT FROM AUTHOR]

This work presents the design of a real-time system to model visual objects with the use of self-organising networks. The architecture of the system addresses multiple computer vision tasks such as image segmentation, optimal parameter estimation and object representation. We first develop a framework for building non-rigid shapes using the growth mechanism of the self-organising maps, and then we define an optimal number of nodes without overfitting or underfitting the network based on the knowledge obtained from information-theoretic considerations. We present experimental results for hands and faces, and we quantitatively evaluate the matching capabilities of the proposed method with the topographic product. The proposed method is easily extensible to 3D objects, as it offers similar features for efficient mesh reconstruction. [ABSTRACT FROM AUTHOR]

In this survey paper, we report the results of a comprehensive study involving the application of dynamic self-organizing neural networks (SONNs) to the problem of novelty detection in time series data. The study is comprised of three main parts. In the first part, we aim at evaluating how the performances of nonrecurrent dynamic SONNs are influenced by the introduction of different short-term memory kernels, such as Gamma, Gamma II and Laguerre, in the network input. In the second part, we analyze the performances of recurrent dynamic SONNs with the goal of inferring if they possess or not any competitive advantage over nonrecurrent architectures for novelty detection in time series. Finally, in the third part of the study, we introduce an alternative approach for dynamic SONN-based novelty detection by revisiting the operator map framework introduced by Lampinen and Oja (Proceedings of the 6th Scandinavian conference on image analysis (SCIA’89), pp 120-127, 1989) and Lehtimäki et al. (Proceedings of the joint international conference on artificial neural networks and neural information processing (ICANN/ICONIP’2003), pp 622-629, 2003). This framework allows the design of dynamic SONNs whose neurons are regarded as adaptive local linear models. In this case, novel/abnormal patterns are detected based on the statistics of prediction errors of the local models. A comprehensive performance comparison involving several nonrecurrent and recurrent dynamic SONN architectures is carried out using both synthetic and real-world time series data. [ABSTRACT FROM AUTHOR]

We propose and evaluate a system for content-based visualization and exploration of music collections. The system is based on a modification of Kohonen’s Self-Organizing Map algorithm and allows users to choose the locations of clusters containing acoustically similar tracks on the music space. A user study conducted to evaluate the system shows that the possibility of personalizing the music space was perceived as difficult. Conversely, the user study and objective metrics derived from users’ interactions with the interface demonstrate that the proposed system helped individuals create playlists faster and, under some circumstances, more effectively. We believe that personalized browsing interfaces are an important area of research in Multimedia Information Retrieval, and both the system and user study contribute to the growing work in this field. [ABSTRACT FROM AUTHOR]

In previous works, we proposed two methods for data clustering based on automatically discovered fuzzy predicates which were referred to as SOM-based Fuzzy Predicate Clustering (SFPC) [Meschino et al., Neurocomputing, 147, 47–59 (2015)] and Type-2 Data-based Fuzzy Predicate Clustering (T2-DFPC) [Comas et al., Expert Syst. Appl., 68, 136–150 (2017)]. In such methods, fuzzy predicates allow both data clustering and knowledge discovering about the obtained clusters. This last feature constitutes novelty comparing to other existing approaches and it is a major contribution in the data clustering field. Based on these previous methods, in the present paper a new automatic clustering method based on fuzzy predicates is proposed which uses Self-Organizing Maps (SOMs) and is called Type-2 SOM-based Fuzzy Predicate Clustering (T2-SFPC). The new method does not require any prior knowledge about the clustering addressed. First, a random partition is defined on the dataset to be clustered and SOMs are configured and trained using the resulting data subsets. Second, an automatic clustering approach is applied on the SOM codebooks, discovering representative data of the different clusters, which are called cluster prototypes. Third, interval type-2 membership function formed by Gaussian-shape sub-functions and fuzzy predicates are defined, allowing data clustering and its interpretation. The proposed method preserves all the advantages of the previous methods SFPC and T2-DFPC in relation to the knowledge extraction capabilities and their potential application on distributed clustering and parallel computing, but results obtained on several public datasets tested showed more compactness and separation of the clusters defined by the T2-SFPC, outperforming both the previous methods and the several classical clustering approaches tested, considering internal and external validation indices. Additionally, both clustering interpretation and optimization capabilities are improved by the proposed method when compared to the methods SFPC and T2-DFPC. [ABSTRACT FROM AUTHOR]

The authors developed a self-organizing map-based optimization (SOMO) neurofuzzy classifier to deal with a practical expatriation willingness (EW) problem, which is associated with employees’ willingness to accept expatriate assignments. The proposed model also delivers more information about rule coverage and generates user-friendly outcomes. The authors adopt the SOMO algorithm to optimize the weights of neurons in the proposed hybrid neurofuzzy classifier. They evaluated the model’s feasibility using the databases from previous studies exploring employees’ EW. The results show that the proposed neurofuzzy classifier yields 11 determination rules whose accuracy rates are greater than 80 percent. The contribution to the body of knowledge lies in the significant improvement in accuracy rates and coverage for predicting EW rules, optimization for all the network parameters using a novel algorithm, and more friendly outputs for practical use. [ABSTRACT FROM PUBLISHER]

The self-organizing maps (SOMs) approach is demonstrated as a way to identify a range of archetypal largescale meteorological patterns (LSMPs) over the northwestern United States and connect these patterns with local-scale temperature and precipitation extremes. SOMs are used to construct a set of 12 characteristic LSMPs (nodes) based on daily reanalysis circulation fields spanning the range of observed synoptic-scale variability for the summer and winter seasons for the period 1979–2013. Composites of surface variables are constructed for subsets of days assigned to each node to explore relationships between temperature, precipitation, and the node patterns. The SOMs approach also captures interannual variability in daily weather regime frequency related to El Niño–Southern Oscillation. Temperature and precipitation extremes in high resolution gridded observations and in situ station data show robust relationships with particular nodes in many cases, supporting the approach as a way to identify LSMPs associated with local extremes. Assigning days from the extreme warm summer of 2015 and wet winter of 2016 to nodes illustrates how SOMs may be used to assess future changes in extremes. These results point to the applicability of SOMs to climate model evaluation and assessment of future projections of local-scale extremes without requiring simulations to reliably resolve extremes at high spatial scales. [ABSTRACT FROM AUTHOR]

In recent years, the growth of marine traffic in ports and their surroundings raise the traffic and security control problems and increase the workload for traffic control operators. The automated identification system of vessel movement generates huge amounts of data that need to be analysed to make the proper decision. Thus, rapid self-learning algorithms for the decision support system have to be developed to detect the abnormal vessel movement in intense marine traffic areas. The paper presents a new self-learning adaptive classification algorithm based on the combination of a self-organizing map (SOM) and a virtual pheromone for abnormal vessel movement detection in maritime traffic. To improve the quality of classification results, Mexican hat neighbourhood function has been used as a SOM neighbourhood function. To estimate the classification results of the proposed algorithm, an experimental investigation has been performed using the real data set, provided by the Klaipėda seaport and that obtained from the automated identification system. The results of the research show that the proposed algorithm provides rapid self-learning characteristics and classification. [ABSTRACT FROM AUTHOR]

The laser-induced breakdown spectroscopy (LIBS) technique was used for analyzing the composition of an ancient Roman mortar (5th century A.D.), exploiting an experimental setup which allows the determination of the compositions of binder and aggregate in few minutes, without the need for sample treatment. Four thousand LIBS spectra were acquired from an area of 10 mm2, with a 50 mm lateral resolution. The elements of interest in the mortar sample (H, C, O, Na, Mg, Al, Si, K, Ca, Ti, Mn, Fe) were detected and mapped. The collected data graphically shown as compositional images were interpreted using different statistical approaches for the determination of the chemical composition of the binder and aggregate fraction. The methods of false color imaging, blind separation, and self-organizing maps were applied and their results are discussed in this paper. In particular, the method based on the use of self-organizing maps gives well interpretable results in very short times, without any reduction in the dimensionality of the system. [ABSTRACT FROM AUTHOR]

In order to suppress the interference in local area networks, this paper presents a Wireless Local Area Networks (WLAN) interference self-optimization method based on a Self-Organizing Feature Map (SOM) neural network model. This method trains the model by using original data sets as the initial vector set and using the whole Signal to Interference plus Noise Ratio (SINR) vector generated by the change of one Wireless Access Point (AP) channel as the basic feature. After the training, the SOM neural network can quickly locate the fault AP and optimize the network according to the changes of the network environment. Simulation results reveal that the proposed scheme can efficiently locate the AP where interference happens and optimize the interference with an improved user experience. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Fabric prints may contain intricate and nesting color patterns. To evaluate colors on such a fabric, regions of different colors must be measured individually. Therefore, precise separation of colored patterns is paramount in analyzing fabric colors for digital printing, and in assessing the colorfastness of a printed fabric after a laundering or abrasion process. This paper presents a self-organizing-map (SOM) based clustering algorithm used to automatically classify colors on printed fabrics and to accurately partition the regions of different colors for color measurement. The main color categories of an image are firstly identified and flagged using the SOM's density map and U-matrix. Then, the region of each color category is located by divining the U-matrix map with an adaptive threshold, which is determined by recursively decreasing it from a high threshold until all the flagged neurons are assigned to different regions in the divided map. Finally, the regions with high color similarity are merged to avoid possible over-segmentation. Unlike many other clustering algorithms, this algorithm does not need to pre-define the number of clusters (e.g. main colors) and can automatically select a distance threshold to partition the U-matrix map. The experimental results show that the intricate color patterns can be precisely separated into individual regions representing different colors. [ABSTRACT FROM AUTHOR]

Self-organizing neural networks are excellent tools for data processing, pattern recognition, cluster analysis and more. SOMs provide a discretized representation of the input space to allow for more efficient processing and analysis. While neural networks have historically focused on the emulation of information processing by animal brains, analyzing the existing self-organizing paradigms has suggested that it could be possible to achieve quality results not only by emulating the human brain, but also by mimicking one of the fundamental forces of the universe—gravity. This paper features an algorithm, GORMANN, which utilizes Newton's law of universal gravitation to attract neurons to input data. The gravitational attraction of the data on the neurons produces results that are analogous to a cross between a SOM and an image processed by morphological thinning: the key features of the input are extracted and discretized. This has the effect of maintaining a topology similar to the input pattern while ignoring superfluous information. Current research has utilized morphological thinning for a variety of fields such as micro-blood vessel detection and real-world map analysis. In this paper, GORMANN is compared with the Kohonen SOM and morphological thinning on a number of 2D input patterns. We will show that GORMANN produces excellent results in very few iterations. [ABSTRACT FROM AUTHOR]

Consider the decision faced by the user of a social media site of whether or not to accept a friendship request from another user, given the limited amount of information available before deciding. We formalize the problem by defining the expected utility trade-offs derived from the request and simulate the resulting incentives numerically. These incentives provide the basis on which to build social networks determined by the different expectations and preferences of their users. Social networks are generated using a self-organizing map to cluster the decision makers (DMs) by their friendship acceptance behaviour. This behaviour is determined by the distribution of requesters relative to the preferences of the DMs. [ABSTRACT FROM AUTHOR]

As an emerging IT-driven business paradigm, smart product-service system (Smart PSS), which offers not only the smart, connected product (SCP) but also its generated service as a solution bundle, has become a vital research topic. Many research efforts have been devoted to constructing the conceptual design framework by considering SCPs and services simultaneously. However, the following critical issues in Smart PSS conceptual design have not been well addressed: how to improve the solution of Smart PSS in the conceptual design stage to meet user emotional requirements. Aiming to fill the gap, this work proposes a conceptual design method for Smart PSS from the perspective of analyzing user-generated emotions/feelings. Specifically, the relevant traditional products are identified, and their public review data is used to analyze user emotions/feelings in user-product interaction. Interactive emotion board as a new design tool is presented to organize the user-generated emotions/feelings, associated design elements, and the potential design points of the initial solution. And the analytic hierarchy process (AHP) is utilized to evaluate the improved solution. To ensure the efficiency of the analysis process, the self-organizing map (SOM) algorithm is utilized in the process of clustering product samples and Kansei words. A case study of smart electric bicycle service system (SEBSS) design is used to demonstrate the performance of the proposed method. Based on the case study, the proposed approach appears effective in helping with Smart PSS conceptual design. [ABSTRACT FROM AUTHOR]

The aim of this study is to cluster landforms in the west of the Fars province, Iran using selforganizing maps (SOM). According to qualitative data, the clustering tendencies of landforms are investigated using six morphometric parameters, which are slope, profile, plan, elevation, curvature and aspect. First, topographic position index (TPI) is used to prepare the landform classification map. The results of SOM show that there are five classes for landform classification in the study area. Cluster 5 corresponds to high slope, high elevation but with different of concavity and convexity that consist of ridge landforms, while Cluster 3 corresponds to flat areas, possibly plantation areas, in medium elevation and almost flat terrain. Clusters 1, 2 and 4 correspond to channels with different slope conditions. [ABSTRACT FROM AUTHOR]

The paper describes a proposal for interactive visualization for exploratory data mining models generated with association rule technique, applying the Self-Organizing Map (SOM) technique on each component or rule, with a view provided by graphic elements implemented to complement this visualization. This seeks to establish visualization schemes, which support the visual exploration stage model fit of a data mining process, and with this answer generic questions regarding data analysts inner workings of the model, and achieve support in understanding generated model. This proposed scheme is implemented visualization through experimental software where data analysts have different interaction mechanisms that allow them to interact and explore each component model, with additional views described above. Finally, results from a controlled experiment, conducted with a group of users whose preliminary analysis of this evaluation allow one hand confirm the usefulness of the proposed scheme on display models of association rules, and analyzes level of efficiency in support understanding of the generated model. [ABSTRACT FROM AUTHOR]

A study on using an unsupervised learning technique, called a self-organizing map (SOM) or Kohonen map, for the detection of road cracks from pavement images is described in this paper. The main focus is on highly textured road images that make the crack detection very difficult. Road images are split into smaller rectangular cells, and a representative data set is generated for each cell by analyzing image texture and color properties. Texture and color properties are combined with a Kohonen map to distinguish crack areas from the background. Using this technique, cracks are detected to a precision of 77%. The algorithm also resulted in a recall of 73% despite the background having very strong visual texture. The technique applied here shows a great deal of promise despite the images being captured in an uncontrolled environment devoid of state-of-the-art image-acquisition setups. The results are also benchmarked against an advanced algorithm reported in a recent research paper. The benchmarking shows that the proposed algorithm performs better in terms of reducing the false positives in crack detection. [ABSTRACT FROM AUTHOR]

In this article, we investigate self-organizing optimization for cognitive small cells (CSCs), which have the ability to sense the environment, learn from historical information, make intelligent decisions, and adjust their operational parameters. By exploring the inherent features, some fundamental challenges for self-organizing optimization in CSCs are presented and discussed. Specifically, the dense and random deployment of CSCs brings about some new challenges in terms of scalability and adaptation; furthermore, the uncertain, dynamic, and incomplete information constraints also impose some new challenges in terms of convergence and robustness. For providing better service to users and improving resource utilization, four requirements for self-organizing optimization in CSCs are presented and discussed. Following the attractive fact that the decisions in game-theoretic models are exactly coincident with those in self-organizing optimization (i.e., distributed and autonomous), we establish a framework of gametheoretic solutions for self-organizing optimization in CSCs and propose some featured game models. Specifically, their basic models are presented, some examples are discussed, and future research directions are given. [ABSTRACT FROM PUBLISHER]

In this paper we are going to describe the steps that conform a novel approach for representation of multidimensional datasets through the proposed Framework nD-EVM/Kohonen. In this sense two phases are going to be taken in account: 1) the application of 1-Dimensional Kohonen Self-Organizing Maps (1D-KSOMs) in order to achieve (n-1)D hypervoxelizations' segmentations, n ≥ 2, taking in account their geometrical and topological properties to characterize the information contained in the datasets. 2) The segmented multidimensional datasets are specified as Orthogonal Polytopes whose n-th Dimension is associated to a 1D-KSOM classification. Subsequently, the nD representation is concisely expressed via the Extreme Vertices Model in the n-Dimensional Space (nD-EVM). There is presented a comparative analysis based on the use of False Color Maps in order to understand they way our considered 1D-KSOMs distribute appropriately their weights vectors along the classification space, even better than classifications based exclusively on color intensity. Additionally, we present some arguments to sustain that a 1D-KSOM is an adequate option in terms of temporal complexity and, on the other hand, that our representation is concise in terms of spatial complexity because of the nD-EVM properties. [ABSTRACT FROM AUTHOR]

Because an ecological community consists of diverse species that vary nonlinearly with environmental variability, its dynamics are complex and difficult to analyze. To investigate temporal variations of benthic macroinvertebrate community, we used the community data that were collected at the sampling site in Baenae Stream near Busan, Korea, which is a clean stream with minimum pollution, from July 2006 to July 2013. First, we used a self-organizing map (SOM) to heuristically derive the states that characterizes the biotic condition of the benthic macroinvertebrate communities in forms of time series data. Next, we applied the hidden Markov model (HMM) to fine-tune the states objectively and to obtain the transition probabilities between the states and the emission probabilities that show the connection of the states with observable events such as the number of species, the diversity measured by Shannon entropy, and the biological water quality index (BMWP). While the number of species apparently addressed the state of the community, the diversity reflected the state changes after the HMM training along with seasonal variations in cyclic manners. The BMWP showed clear characterization of events that correspond to the different states based on the emission probabilities. The environmental factors such as temperature and precipitation also indicated the seasonal and cyclic changes according to the HMM. Though the usage of the HMM alone can guarantee the convergence of the training or the precision of the derived states based on field data in this study, the derivation of the states by the SOM that followed the fine-tuning by the HMM well elucidated the states of the community and could serve as an alternative reference system to reveal the ecological structures in stream communities. [ABSTRACT FROM AUTHOR]

A neural network technique known as Kohonen unsupervised training is coupled with a modified version of the particle swarm optimization technique in an effort to develop an algorithm capable of finding multiple optimal solutions for a given problem. The ability to find multiple optimal solutions is of interest in many different applications, such as complex engineering design problems, where it's beneficial to analyze more than one potential design or solution. The results of five example problems of increasing difficulty validate the Alternative Analysis Networking algorithm's functionality. This algorithm is an efficient and robust technique, and appears to be the first capable of performing the task of finding multiple optimal solutions as efficiently as typical stochastic-based optimizers. [ABSTRACT FROM AUTHOR]