Improving visualisation and prediction performance of supervised self-organising map by modified contradiction resolution

We have previously proposed a new type of information-theoretic method where a neuron is evaluated by itself (self-evaluation) and by its surrounding neurons (outer-evaluation). If contradiction between different types of evaluation exists, it is reduced as much as possible. In the present paper, we try to separate self- and outer-evaluation more explicitly and introduce the importance of neurons. First, we separate self- and outer-evaluation to enhance the characteristics shared by the two types of evaluation. Second, we introduce the importance of neurons in evaluation. By using a limited number of important neurons in evaluation, we expect the main characteristics in input patterns to emerge. We applied this contradiction resolution to two types of data, namely, the Senate data and the Euro-yen exchange rates. In both data sets, experimental results confirmed that improved prediction performance was obtained. Prediction performance was better than that obtained by the conventional self-organising map (SOM) and radial basis function networks. In addition, final representations obtained by contradiction resolution were easier to interpret than those given by the conventional SOM. Experimental results confirmed that improved interpretation and visualisation were accompanied by improved prediction performance.     

Genetic algorithm and self organizing map based fuzzy hybrid intelligent method for color image segmentation

The grouping of pixels based on some similarity criteria is called image segmentation. In this paper the problem of color image segmentation is considered as a clustering problem and a fixed length genetic algorithm (GA) is used to handle it. The effectiveness of GA depends on the objective function (fitness function) and the initialization of the population. A new objective function is proposed to evaluate the quality of the segmentation and the fitness of a chromosome. In fixed length genetic algorithm the chromosomes have same length, which is normally set by the user. Here, a self organizing map (SOM) is used to determine the number of segments in order to set the length of a chromosome automatically. An opposition based strategy is adopted for the initialization of the population in order to diversify the search process. In some cases the proposed method makes the small regions of an image as separate segments, which leads to noisy segmentation. A simple ad hoc mechanism is devised to refine the noisy segmentation. The qualitative and quantitative results show that the proposed method performs better than the state-of-the-art methods.     

自动驾驶仪神经网络控制的HLA仿真研究

在对空空导弹自动驾驶仪各功能模块需求和能力分析的基础上,以组件的重用和可扩展为目标,运用HLA技术划分各联邦成员,成功组建神经网络自动驾驶仪分布式仿真系统。设计过程中的关键技术如对FOM/SOM设计和Simulink模型代码转换分别做了研究,给出了基于Matlab/Simulink所建立的空空导弹自动驾驶仪神经网络控制算法与HLA集成的一个工程样例。     

Image segmentation scheme based on SOM–PCNN in frequency domain

A hybrid scheme for the image segmentation of high-resolution images is proposed in this study. Our methodology is based on combining both supervised and unsupervised segmentation. The entire process is performed in the frequency domain, rather than the spatial domain, using the Shift Invariant Shearlet Transform (SIST). Initially, the input image is filtered using an anisotropic filter to enhance the texture features. Then, it is separated into low and high sub-band frequencies using SIST. Subsequently, we built a feature vector from coarser coefficients complemented with texture information extracted from high-frequency coefficients of the input image. SOM is used for the preliminary classification of the input image coefficients, and the network training process is performed using the previously built feature vector. Lastly, the modified PCNN is used to augment the SOM results to reduce the over-segmentation artefacts. We used the Berkeley Segmentation Database (BSR) and Quick-Bird Satellite images to validate the results. It was found that the proposed scheme is superior to the Fuzzy-C-Means-based, SOM-based, and PCNN-based segmentation algorithms in terms of quantitative criteria and visual interpretation.     

An unsupervised learning method with a clustering approach for tumor identification and tissue segmentation in magnetic resonance brain images

Malignant and benign types of tumor infiltrated in human brain are diagnosed with the help of an MRI scanner. With the slice images obtained using an MRI scanner, certain image processing techniques are utilized to have a clear anatomy of brain tissues. One such image processing technique is hybrid self-organizing map (SOM) with fuzzy K means (FKM) algorithm, which offers successful identification of tumor and good segmentation of tissue regions present inside the tissues of brain. The proposed algorithm is efficient in terms of Jaccard Index, Dice Overlap Index (DOI), sensitivity, specificity, peak signal to noise ratio (PSNR), mean square error (MSE), computational time and memory requirement. The algorithm proposed through this paper has better data handling capacities and it also performs efficient processing upon the input magnetic resonance (MR) brain images. Automatic detection of tumor region in MR (magnetic resonance) brain images has a high impact in helping the radio surgeons assess the size of the tumor present inside the tissues of brain and it also supports in identifying the exact topographical location of tumor region. The proposed hybrid SOM-FKM algorithm assists the radio surgeon by providing an automated tissue segmentation and tumor identification, thus enhancing radio therapeutic procedures. The efficiency of the proposed technique is verified using the clinical images obtained from four patients, along with the images taken from Harvard Brain Repository.     

Can Tolerant Diatom Taxa be Used for Effective Assessments of Human Pressure?

Because lately the low bioindicative value of tolerant species from different taxonomic groups is often questioned, in this study, we hypothesized that tolerant diatoms may be used for effective temporal assessments of human pressure. We tested this on the lowland Bzura River in central Poland, on 156 diatom samples (DSs) from two study periods of 1972 with extremely severe point‐source water pollution and of 2002–2004, where the complex wastewater management in the river catchment improved water quality considerably. Out of the total 295 diatom species recorded in the samples, only 133 tolerant ones were included in the study. Patterns in their abundance were recognized with a Kohonen artificial neural network (self‐organizing map, SOM), whereas the species significantly associated with each SOM cluster of diatom samples were identified with the indicator value (IndVal) index and the Monte Carlo test. If the hypothesis tested was not supported, the assignation of DSs to the SOM clusters would be random. However, the separation of DSs from 1972 and 2002–2004 was almost perfect because the number of exceptions was as low as 4.5%. In addition, the relatively high number (64 out of 133) of tolerant species significantly associated with any SOM cluster (and respective environmental conditions at sites from which samples assigned to it come) supports the hypothesis tested. This means that almost half of the studied species are not evenly distributed in particular clusters as might be expected for highly tolerant species. The study proves that the abundances of many diatom species, currently classified as tolerant, carry quite precise information on the differences in the quality of the environment, and indicates those tolerant diatom species whose bioindicative potential may be highest. Copyright © 2014 John Wiley & Sons, Ltd.     

一种面向订单剩余完工时间预测的SOM-FWFCM特征选择算法#br#

准确的订单剩余完工时间预测有助于动态调整生产计划、优化制造过程,以满足订单产品按时交付的需求。订单剩余完工时间受到车间物料、设备、在制品等各类生产要素的综合影响,相关数据具有典型的大量、多维、高冗余的特点,有效的特征选择能够获得更高的预测精度。在构建候选特征集的基础上,提出了一种基于自组织映射（SOM）网络特征加权模糊C均值（FWFCM）的特征选择算法。通过构建SOM网络初始化FWFCM的聚类中心,减少后者对初始聚类中心的依赖;基于互信息计算特征权重,实现导向性特征聚类,根据聚类结果选择特征代表,构成高质量关键特征子集。以某机加工车间的生产数据为例,通过与其他4种特征选择算法的对比分析,验证了所提算法的有效性。     

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.     

A direct electrochemical route from oxides to Ti-Si intermetallics

The titanium silicide intermetallics have been directly prepared from the mixture of titanium oxide (TiO₂) and silicon oxide (SiO₂) powder by using the solid-oxygen-ion-conducting membrane (SOM) electrolysis process. The electrochemical process was carried out in a molten flux CaCl₂ at 950 °C with a potential of 3.5-4.0 V. The effects of the stoichiometry of the initial mixture on the electrolysis characteristics and the final product compositions were investigated. It has been found that the molar ratio of TiO₂:SiO₂ dominates the composition of final products. A single-phase silicide Ti₅Si₃ intermetallic was obtained when the TiO₂:SiO₂ molar ratio is 5:3; the TiSi was identified as the dominant phase with a minor amount of TiSi₂ at TiO₂:SiO₂ molar ratio 1:1; three silicide phases, Ti₅Si₄, Ti₅Si₃ and TiSi, were found coexisting in the final product produced from TiO₂-SiO₂ mixture of molar ratio 5:4; the product of electrolysis consisted of the compound Ti₅Si₃ and the pure metal Ti as TiO₂:SiO₂ molar ratio equals to 3:1; and two silicide phases, TiSi and TiSi₂, are formed as TiO₂:SiO₂ molar ratio equals to 1:2. The preliminary experimental results suggest that the electro-deoxidization process is fast and the current efficiency reached 75%.     

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.