Cuticular hydrocarbons of Tetramorium ants from central Europe: analysis of GC-MS data with self-organizing maps (SOM) and implications for systematics

Cuticular hydrocarbons were extracted from workers of 63 different nests of five species of Tetramorium ants (Hymenoptera: Formicidae) from Austria, Hungary, and Spain. The GC-MS data were classified (data mining) by self-organizing maps (SOM). SOM neurons derived from primary neuron separation were subjected to hierarchical SOM (HSOM) and were grouped to neuron areas on the basis of vicinity in the hexagonal output grid. While primary neuron separation and HSOM resulted in classifications on a level more sensitive than species differences, neuron areas resulted in chemical phenotypes apparently of the order of species. These chemical phenotypes have implications for systematics: while the chemical phenotypes for T. ferox and T. moravicum correspond to morphological determination, in T. caespitum and T. impurum a total of six chemical phenotypes is found. Three hypotheses are discussed to explain this disparity between morphological and chemical classifications, including in particular the possibility of hybridization and the existence of cryptic species. Overall, the GC-MS profiles classified by SOM prove to be a practical alternative to morphological determination (T. ferox, T. moravicum) and indicate the need to revisit systematics (T. caespitum, T. impurum).     

Improvement of borrowing channel assignment for patterned traffic load by online cellular probabilistic self-organizing map

This paper describes an improvement of borrowing channel assignment (BCA) for patterned traffic load by using the short-term traffic prediction ability of cellular probabilistic self-organizing map (CPSOM). The fast growing cellular mobile systems demand more efficient and faster channel allocation techniques today. In case of patterned traffic load, the traditional BCA methods are not efficient to further enhance the performance because heavy-traffic cells cannot borrow channels from their neighboring cells with light or medium traffic that may have unused nominal channels. The performance can be increased if the short-term traffic load can be predicted. The predicted results can then be used for channel re-assignment. Therefore, the unused nominal channels of the light-or-medium-traffic cells can be transferred to the heavy-traffic cells that need more nominal channels. In this paper, CPSOM is used online for traffic prediction. In this sense, the proposed CPSOM-based BCA method is able to enhance the performance for patterned traffic load compared with the traditional BCA methods. Simulation results corroborate that the proposed method enables the system to work with better performance for patterned traffic load than the traditional BCA methods.     

Real-time multiple people tracking using competitive condensation

The CONDENSATION (Conditional Density Propagation) algorithm has a robust tracking performance and suitability for real-time implementation. However, the CONDENSATION tracker has some difficulties with real-time implementation for multiple people tracking since it requires very complicated shape modelling and a large number of samples for precise tracking performance. Further, it shows a poor tracking performance in the case of close or partially occluded people. To overcome these difficulties, we present three improvements: First, we construct effective templates of people's shapes using the SOM (Self-Organizing Map). Second, we take the discrete HMM (Hidden Markov Modelling) for an accurate dynamical model of the people's shape transition. Third, we use the competition rule to separate close or partially occluded people effectively. Simulation results shows that the proposed CONDENSATION algorithm can achieve robust and real-time tracking in the image sequences of a crowd of people.     

一种基于SOM的中文文本两阶段快速聚类方法应用研究

研究了一种基于自组织神经网络的中文文档聚类方法,按照提出的中文聚类模型,该方法首先对文档进行SOM训练产生初步的聚类结果,然后对第一次聚类结果进行基于参考点和密度的快速聚类,理论分析和实验结果也证明了该方法适合高维中文文档的聚类,与直接聚类方法相比,该方法提高了聚类的效果,减少了计算时间。     

飞机故障诊断专家系统的软件实现

首先提出了开发飞机故障诊断专家系统的必要性 ,并简要说明了笔者所研制的软件的知识基础和设计与实现方法 ;介绍了基于事例的推理 (Case BasedReasoning ,CBR)的优越性 ,重点说明了该软件中事例的来源和事例库的构造 ;并详细介绍了自组织特征映射网络 (SelfOrganizingMap,SOM) ,以及其在该软件中的实现算法和程序结构简图 ;最后分析了该软件广泛的应用前景。     

Ta2O5直接制备金属钽的研究

利用固体透氧膜（SOM）法对Ta2O5直接电解制备金属钽进行了研究。Ta2O5粉经压片烧结后制成阴极，氧化钇稳定氧化锫管内的碳饱和铜液为阳极，混合熔盐MgF2-CaF2为电解质，在1150℃不同电压下进行电解。经XRD，SEM等分析表明：在透氧膜稳定的条件下，电压越高，脱氧速度越快。该方法制备金属钽具有电解速度快、电流密度高等优点，发展前景良好。     

Modified self-organising maps with a new topology and initialisation algorithm

Mapping quality of the self-organising maps (SOMs) is sensitive to the map topology and initialisation of neurons. In this article, in order to improve the convergence of the SOM, an algorithm based on split and merge of clusters to initialise neurons is introduced. The initialisation algorithm speeds up the learning process in large high-dimensional data sets. We also develop a topology based on this initialisation to optimise the vector quantisation error and topology preservation of the SOMs. Such an approach allows to find more accurate data visualisation and consequently clustering problem. The numerical results on eight small-to-large real-world data sets are reported to demonstrate the performance of the proposed algorithm in the sense of vector quantisation, topology preservation and CPU time requirement.     

Quantitative identification of illicit drugs by using SOM neural networks

Qualitative identification of THz spectra of illicit drugs using self-organization feature map (SOM) artificial neural network has been demonstrated. In this paper, investigation results show that SOM has quantitatively identified drug mixtures successfully. Based on Beer’s law THz spectra data of various drug proportions were made for training dates. After analyzing the clustering algorithm of SOM, we introduced a parameter named shortest distance as a quantitative criterion for identification result. By this parameter, an automatic recognition algorithm has been developed and successfully applied to the content identification of experimental samples. Combined with our previous work, the SOM neural network can be an integrated and effective method in the identification the THz spectra of illicit drugs.     

Discrimination of base oils and semi-products using principal component analysis and self organizing maps

¹H NMR spectroscopy, combined with pattern recognition techniques (PCA and SOM) was used in discriminating base oils and refinery-intermediate products. Both PCA and SOM enabled correct oil discrimination into groups in accordance with API 1509. Moreover, information about the structural compositions of the samples, correlated with their physical and chemical properties, was provided. The PCA score plot enabled component identification and semiquantitative analysis of binary mixtures of base oils, including semisynthetic oils.     

Management of organic matter in the tropics: translating theory into practice

Inputs of organic materials play a central role in the productivity of many tropical farming systems by providing nutrients through decomposition and substrate for synthesis of soil organic matter (SOM). The organic inputs in many tropical farming systems such as crop residues, manures, and natural fallows are currently of low quality and insufficient quantity to maintain soil fertility hence there is need to find alternative or supplementary sources of nutrients. Knowledge gained over the past decade on the role of organic resource quality in influencing soil nutrient availability patterns (Synchrony Principle) and SOM maintenance (SOM Principle) provides a strong scientific basis on which to develop management tools. This scientific information must be linked with farmer knowledge and circumstances to provide a realistic approach to soil fertility and SOM management in the tropics. A decision tree has been developed for testing hypotheses about the resource quality parameters that affect nitrogen release patterns and rates. The decision tree is linked to an Organic Resource Database (ORD) with detailed information on the resource quality of agroforestry trees and leguminous cover crops providing a systematic means of selecting organic resources for soil fertility management. The decision tree has also been translated into a practical field guide for use with farmers in evaluating organic materials. The longer-term effects of organic inputs on SOM might also be addressed through the decision tree and database. It is generally believed that materials good for short-term soil fertility will not build or maintain SOM; if true then it is difficult to imagine practical means of maintaining SOM in the African context where short-term fertility issues will take precedence over longer-term maintenance of SOM. This revised version was published online in June 2006 with corrections to the Cover Date.